diff --git a/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step52452_2022-12-28-10-34-30.csv b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step52452_2022-12-28-10-34-30.csv new file mode 100644 index 0000000000000000000000000000000000000000..5ff0e272316f7e71ad0128c0842b8ce432975453 --- /dev/null +++ b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step52452_2022-12-28-10-34-30.csv @@ -0,0 +1,21 @@ +task,metric,value,err,version +anli_r1,acc,0.286,0.014297146862517908,0 +anli_r2,acc,0.304,0.01455320568795044,0 +anli_r3,acc,0.3175,0.013443538681348054,0 +arc_challenge,acc,0.26535836177474403,0.012902554762313969,0 +arc_challenge,acc_norm,0.2909556313993174,0.013273077865907573,0 +arc_easy,acc,0.5122053872053872,0.010256726235129016,0 +arc_easy,acc_norm,0.4877946127946128,0.01025672623512901,0 +boolq,acc,0.6862385321100918,0.008115773046958279,1 +cb,acc,0.35714285714285715,0.06460957383809221,1 +cb,f1,0.27666815942678014,,1 +copa,acc,0.69,0.04648231987117316,0 +hellaswag,acc,0.4907388966341366,0.004988925410522774,0 +hellaswag,acc_norm,0.5834495120493925,0.00491979470467327,0 +piqa,acc,0.6605005440696409,0.011048455047173918,0 +piqa,acc_norm,0.6534276387377584,0.011103020320872166,0 +rte,acc,0.5631768953068592,0.029855247390314945,0 +sciq,acc,0.905,0.009276910103103324,0 +sciq,acc_norm,0.872,0.010570133761108658,0 +storycloze_2016,acc,0.5879208979155531,0.011382271506935862,0 +winogrande,acc,0.5177584846093133,0.014043619596174966,0 diff --git a/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step52452_2022-12-28-10-34-30.json b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step52452_2022-12-28-10-34-30.json new file mode 100644 index 0000000000000000000000000000000000000000..fdbf96b4feecffde184d7d1c52c06e803587681a --- /dev/null +++ b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step52452_2022-12-28-10-34-30.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.286, + "acc_stderr": 0.014297146862517908 + }, + "anli_r2": { + "acc": 0.304, + "acc_stderr": 0.01455320568795044 + }, + "anli_r3": { + "acc": 0.3175, + "acc_stderr": 0.013443538681348054 + }, + "cb": { + "acc": 0.35714285714285715, + "acc_stderr": 0.06460957383809221, + "f1": 0.27666815942678014 + }, + "copa": { + "acc": 0.69, + "acc_stderr": 0.04648231987117316 + }, + "hellaswag": { + "acc": 0.4907388966341366, + "acc_stderr": 0.004988925410522774, + "acc_norm": 0.5834495120493925, + "acc_norm_stderr": 0.00491979470467327 + }, + "rte": { + "acc": 0.5631768953068592, + "acc_stderr": 0.029855247390314945 + }, + "winogrande": { + "acc": 0.5177584846093133, + "acc_stderr": 0.014043619596174966 + }, + "storycloze_2016": { + "acc": 0.5879208979155531, + "acc_stderr": 0.011382271506935862 + }, + "boolq": { + "acc": 0.6862385321100918, + "acc_stderr": 0.008115773046958279 + }, + "arc_easy": { + "acc": 0.5122053872053872, + "acc_stderr": 0.010256726235129016, + "acc_norm": 0.4877946127946128, + "acc_norm_stderr": 0.01025672623512901 + }, + "arc_challenge": { + "acc": 0.26535836177474403, + "acc_stderr": 0.012902554762313969, + "acc_norm": 0.2909556313993174, + "acc_norm_stderr": 0.013273077865907573 + }, + "sciq": { + "acc": 0.905, + "acc_stderr": 0.009276910103103324, + "acc_norm": 0.872, + "acc_norm_stderr": 0.010570133761108658 + }, + "piqa": { + "acc": 0.6605005440696409, + "acc_stderr": 0.011048455047173918, + "acc_norm": 0.6534276387377584, + "acc_norm_stderr": 0.011103020320872166 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-01-17-56-56.csv b/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-01-17-56-56.csv new file mode 100644 index 0000000000000000000000000000000000000000..43fe1c6519c189e6791cc79333e91468152c6027 --- /dev/null +++ b/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-01-17-56-56.csv @@ -0,0 +1,120 @@ +task,metric,value,err,version +copa,acc,0.68,0.04688261722621505,0 +hendrycksTest-abstract_algebra,acc,0.28,0.04512608598542127,0 +hendrycksTest-abstract_algebra,acc_norm,0.29,0.045604802157206824,0 +hendrycksTest-anatomy,acc,0.2074074074074074,0.03502553170678318,0 +hendrycksTest-anatomy,acc_norm,0.1925925925925926,0.03406542058502651,0 +hendrycksTest-astronomy,acc,0.21052631578947367,0.03317672787533157,0 +hendrycksTest-astronomy,acc_norm,0.27631578947368424,0.03639057569952924,0 +hendrycksTest-business_ethics,acc,0.34,0.04760952285695236,0 +hendrycksTest-business_ethics,acc_norm,0.29,0.04560480215720683,0 +hendrycksTest-clinical_knowledge,acc,0.20754716981132076,0.02495991802891127,0 +hendrycksTest-clinical_knowledge,acc_norm,0.32452830188679244,0.028815615713432115,0 +hendrycksTest-college_biology,acc,0.25,0.03621034121889507,0 +hendrycksTest-college_biology,acc_norm,0.2361111111111111,0.03551446610810826,0 +hendrycksTest-college_chemistry,acc,0.23,0.042295258468165085,0 +hendrycksTest-college_chemistry,acc_norm,0.31,0.04648231987117316,0 +hendrycksTest-college_computer_science,acc,0.27,0.0446196043338474,0 +hendrycksTest-college_computer_science,acc_norm,0.28,0.04512608598542128,0 +hendrycksTest-college_mathematics,acc,0.26,0.0440844002276808,0 +hendrycksTest-college_mathematics,acc_norm,0.31,0.04648231987117316,0 +hendrycksTest-college_medicine,acc,0.2138728323699422,0.031265112061730424,0 +hendrycksTest-college_medicine,acc_norm,0.26011560693641617,0.03345036916788992,0 +hendrycksTest-college_physics,acc,0.2549019607843137,0.04336432707993178,0 +hendrycksTest-college_physics,acc_norm,0.30392156862745096,0.045766654032077636,0 +hendrycksTest-computer_security,acc,0.29,0.04560480215720684,0 +hendrycksTest-computer_security,acc_norm,0.33,0.047258156262526045,0 +hendrycksTest-conceptual_physics,acc,0.23829787234042554,0.027851252973889764,0 +hendrycksTest-conceptual_physics,acc_norm,0.1574468085106383,0.023809905196619695,0 +hendrycksTest-econometrics,acc,0.24561403508771928,0.04049339297748142,0 +hendrycksTest-econometrics,acc_norm,0.24561403508771928,0.04049339297748142,0 +hendrycksTest-electrical_engineering,acc,0.2896551724137931,0.03780019230438015,0 +hendrycksTest-electrical_engineering,acc_norm,0.2896551724137931,0.03780019230438014,0 +hendrycksTest-elementary_mathematics,acc,0.21428571428571427,0.021132859182754433,0 +hendrycksTest-elementary_mathematics,acc_norm,0.23809523809523808,0.021935878081184756,0 +hendrycksTest-formal_logic,acc,0.2857142857142857,0.04040610178208841,0 +hendrycksTest-formal_logic,acc_norm,0.2857142857142857,0.0404061017820884,0 +hendrycksTest-global_facts,acc,0.18,0.03861229196653694,0 +hendrycksTest-global_facts,acc_norm,0.19,0.039427724440366234,0 +hendrycksTest-high_school_biology,acc,0.20967741935483872,0.023157879349083522,0 +hendrycksTest-high_school_biology,acc_norm,0.2645161290322581,0.02509189237885928,0 +hendrycksTest-high_school_chemistry,acc,0.16748768472906403,0.026273086047535414,0 +hendrycksTest-high_school_chemistry,acc_norm,0.2413793103448276,0.03010833071801162,0 +hendrycksTest-high_school_computer_science,acc,0.23,0.042295258468165044,0 +hendrycksTest-high_school_computer_science,acc_norm,0.23,0.04229525846816505,0 +hendrycksTest-high_school_european_history,acc,0.24242424242424243,0.033464098810559534,0 +hendrycksTest-high_school_european_history,acc_norm,0.26666666666666666,0.03453131801885414,0 +hendrycksTest-high_school_geography,acc,0.20202020202020202,0.028606204289229872,0 +hendrycksTest-high_school_geography,acc_norm,0.2727272727272727,0.03173071239071724,0 +hendrycksTest-high_school_government_and_politics,acc,0.18652849740932642,0.02811209121011748,0 +hendrycksTest-high_school_government_and_politics,acc_norm,0.23834196891191708,0.030748905363909895,0 +hendrycksTest-high_school_macroeconomics,acc,0.2282051282051282,0.021278393863586282,0 +hendrycksTest-high_school_macroeconomics,acc_norm,0.258974358974359,0.02221110681006166,0 +hendrycksTest-high_school_mathematics,acc,0.2222222222222222,0.025348097468097838,0 +hendrycksTest-high_school_mathematics,acc_norm,0.3148148148148148,0.028317533496066468,0 +hendrycksTest-high_school_microeconomics,acc,0.20588235294117646,0.026265024608275882,0 +hendrycksTest-high_school_microeconomics,acc_norm,0.29411764705882354,0.029597329730978093,0 +hendrycksTest-high_school_physics,acc,0.24503311258278146,0.03511807571804724,0 +hendrycksTest-high_school_physics,acc_norm,0.2119205298013245,0.033367670865679766,0 +hendrycksTest-high_school_psychology,acc,0.22201834862385322,0.017818849564796634,0 +hendrycksTest-high_school_psychology,acc_norm,0.23486238532110093,0.018175110510343578,0 +hendrycksTest-high_school_statistics,acc,0.2222222222222222,0.02835321286686346,0 +hendrycksTest-high_school_statistics,acc_norm,0.24537037037037038,0.029346665094372937,0 +hendrycksTest-high_school_us_history,acc,0.28431372549019607,0.03166009679399812,0 +hendrycksTest-high_school_us_history,acc_norm,0.27941176470588236,0.031493281045079556,0 +hendrycksTest-high_school_world_history,acc,0.25738396624472576,0.028458820991460285,0 +hendrycksTest-high_school_world_history,acc_norm,0.2742616033755274,0.029041333510598035,0 +hendrycksTest-human_aging,acc,0.3273542600896861,0.031493846709941306,0 +hendrycksTest-human_aging,acc_norm,0.2645739910313901,0.029605103217038308,0 +hendrycksTest-human_sexuality,acc,0.31297709923664124,0.04066962905677697,0 +hendrycksTest-human_sexuality,acc_norm,0.3282442748091603,0.04118438565806298,0 +hendrycksTest-international_law,acc,0.1652892561983471,0.03390780612972776,0 +hendrycksTest-international_law,acc_norm,0.4462809917355372,0.0453793517794788,0 +hendrycksTest-jurisprudence,acc,0.23148148148148148,0.04077494709252626,0 +hendrycksTest-jurisprudence,acc_norm,0.4074074074074074,0.047500773411999854,0 +hendrycksTest-logical_fallacies,acc,0.1901840490797546,0.030833491146281235,0 +hendrycksTest-logical_fallacies,acc_norm,0.26380368098159507,0.03462419931615623,0 +hendrycksTest-machine_learning,acc,0.33035714285714285,0.044642857142857144,0 +hendrycksTest-machine_learning,acc_norm,0.21428571428571427,0.03894641120044792,0 +hendrycksTest-management,acc,0.17475728155339806,0.037601780060266224,0 +hendrycksTest-management,acc_norm,0.23300970873786409,0.04185832598928315,0 +hendrycksTest-marketing,acc,0.2863247863247863,0.02961432369045665,0 +hendrycksTest-marketing,acc_norm,0.3162393162393162,0.030463656747340244,0 +hendrycksTest-medical_genetics,acc,0.31,0.04648231987117316,0 +hendrycksTest-medical_genetics,acc_norm,0.38,0.04878317312145633,0 +hendrycksTest-miscellaneous,acc,0.25925925925925924,0.015671006009339572,0 +hendrycksTest-miscellaneous,acc_norm,0.2515964240102171,0.01551732236552963,0 +hendrycksTest-moral_disputes,acc,0.2630057803468208,0.02370309952525817,0 +hendrycksTest-moral_disputes,acc_norm,0.3092485549132948,0.02488314057007175,0 +hendrycksTest-moral_scenarios,acc,0.24022346368715083,0.014288343803925293,0 +hendrycksTest-moral_scenarios,acc_norm,0.24692737430167597,0.014422292204808835,0 +hendrycksTest-nutrition,acc,0.24183006535947713,0.024518195641879334,0 +hendrycksTest-nutrition,acc_norm,0.38235294117647056,0.027826109307283686,0 +hendrycksTest-philosophy,acc,0.20257234726688103,0.022827317491059682,0 +hendrycksTest-philosophy,acc_norm,0.28938906752411575,0.025755865922632935,0 +hendrycksTest-prehistory,acc,0.21604938271604937,0.022899162918445803,0 +hendrycksTest-prehistory,acc_norm,0.1882716049382716,0.021751866060815875,0 +hendrycksTest-professional_accounting,acc,0.2375886524822695,0.025389512552729903,0 +hendrycksTest-professional_accounting,acc_norm,0.24468085106382978,0.025645553622266726,0 +hendrycksTest-professional_law,acc,0.2561929595827901,0.011149173153110582,0 +hendrycksTest-professional_law,acc_norm,0.28292046936114734,0.011503891323188976,0 +hendrycksTest-professional_medicine,acc,0.22058823529411764,0.025187786660227248,0 +hendrycksTest-professional_medicine,acc_norm,0.21323529411764705,0.024880971512294275,0 +hendrycksTest-professional_psychology,acc,0.24509803921568626,0.017401816711427667,0 +hendrycksTest-professional_psychology,acc_norm,0.2679738562091503,0.017917974069594726,0 +hendrycksTest-public_relations,acc,0.24545454545454545,0.04122066502878285,0 +hendrycksTest-public_relations,acc_norm,0.2,0.03831305140884603,0 +hendrycksTest-security_studies,acc,0.2979591836734694,0.02927956741106567,0 +hendrycksTest-security_studies,acc_norm,0.2571428571428571,0.02797982353874455,0 +hendrycksTest-sociology,acc,0.31840796019900497,0.03294118479054095,0 +hendrycksTest-sociology,acc_norm,0.3333333333333333,0.03333333333333334,0 +hendrycksTest-us_foreign_policy,acc,0.33,0.04725815626252605,0 +hendrycksTest-us_foreign_policy,acc_norm,0.33,0.047258156262526045,0 +hendrycksTest-virology,acc,0.3072289156626506,0.03591566797824662,0 +hendrycksTest-virology,acc_norm,0.25903614457831325,0.03410646614071855,0 +hendrycksTest-world_religions,acc,0.2982456140350877,0.03508771929824565,0 +hendrycksTest-world_religions,acc_norm,0.3684210526315789,0.036996580176568775,0 +piqa,acc,0.6545157780195865,0.011094802893617745,0 +piqa,acc_norm,0.6605005440696409,0.011048455047173913,0 +rte,acc,0.5234657039711191,0.03006330041190266,0 +winogrande,acc,0.4996053670086819,0.014052481306049516,0 diff --git a/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-01-17-56-56.json b/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-01-17-56-56.json new file mode 100644 index 0000000000000000000000000000000000000000..24802b19b3955184d9da3f9ffc1887cd2bff6c2b --- /dev/null +++ b/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-01-17-56-56.json @@ -0,0 +1,427 @@ +{ + "results": { + "copa": { + "acc": 0.68, + "acc_stderr": 0.04688261722621505 + }, + "piqa": { + "acc": 0.6545157780195865, + "acc_stderr": 0.011094802893617745, + "acc_norm": 0.6605005440696409, + "acc_norm_stderr": 0.011048455047173913 + }, + "rte": { + "acc": 0.5234657039711191, + "acc_stderr": 0.03006330041190266 + }, + "winogrande": { + "acc": 0.4996053670086819, + "acc_stderr": 0.014052481306049516 + }, + "hendrycksTest-abstract_algebra": { + "acc": 0.28, + "acc_stderr": 0.04512608598542127, + "acc_norm": 0.29, + "acc_norm_stderr": 0.045604802157206824 + }, + "hendrycksTest-anatomy": { + "acc": 0.2074074074074074, + "acc_stderr": 0.03502553170678318, + "acc_norm": 0.1925925925925926, + "acc_norm_stderr": 0.03406542058502651 + }, + "hendrycksTest-astronomy": { + "acc": 0.21052631578947367, + "acc_stderr": 0.03317672787533157, + "acc_norm": 0.27631578947368424, + "acc_norm_stderr": 0.03639057569952924 + }, + "hendrycksTest-business_ethics": { + "acc": 0.34, + "acc_stderr": 0.04760952285695236, + "acc_norm": 0.29, + "acc_norm_stderr": 0.04560480215720683 + }, + "hendrycksTest-clinical_knowledge": { + "acc": 0.20754716981132076, + "acc_stderr": 0.02495991802891127, + "acc_norm": 0.32452830188679244, + "acc_norm_stderr": 0.028815615713432115 + }, + "hendrycksTest-college_biology": { + "acc": 0.25, + "acc_stderr": 0.03621034121889507, + "acc_norm": 0.2361111111111111, + "acc_norm_stderr": 0.03551446610810826 + }, + "hendrycksTest-college_chemistry": { + "acc": 0.23, + "acc_stderr": 0.042295258468165085, + "acc_norm": 0.31, + "acc_norm_stderr": 0.04648231987117316 + }, + "hendrycksTest-college_computer_science": { + "acc": 0.27, + "acc_stderr": 0.0446196043338474, + "acc_norm": 0.28, + "acc_norm_stderr": 0.04512608598542128 + }, + "hendrycksTest-college_mathematics": { + "acc": 0.26, + "acc_stderr": 0.0440844002276808, + "acc_norm": 0.31, + "acc_norm_stderr": 0.04648231987117316 + }, + "hendrycksTest-college_medicine": { + "acc": 0.2138728323699422, + "acc_stderr": 0.031265112061730424, + "acc_norm": 0.26011560693641617, + "acc_norm_stderr": 0.03345036916788992 + }, + "hendrycksTest-college_physics": { + "acc": 0.2549019607843137, + "acc_stderr": 0.04336432707993178, + "acc_norm": 0.30392156862745096, + "acc_norm_stderr": 0.045766654032077636 + }, + "hendrycksTest-computer_security": { + "acc": 0.29, + "acc_stderr": 0.04560480215720684, + "acc_norm": 0.33, + "acc_norm_stderr": 0.047258156262526045 + }, + "hendrycksTest-conceptual_physics": { + "acc": 0.23829787234042554, + "acc_stderr": 0.027851252973889764, + "acc_norm": 0.1574468085106383, + "acc_norm_stderr": 0.023809905196619695 + }, + "hendrycksTest-econometrics": { + "acc": 0.24561403508771928, + "acc_stderr": 0.04049339297748142, + "acc_norm": 0.24561403508771928, + "acc_norm_stderr": 0.04049339297748142 + }, + "hendrycksTest-electrical_engineering": { + "acc": 0.2896551724137931, + "acc_stderr": 0.03780019230438015, + "acc_norm": 0.2896551724137931, + "acc_norm_stderr": 0.03780019230438014 + }, + "hendrycksTest-elementary_mathematics": { + "acc": 0.21428571428571427, + "acc_stderr": 0.021132859182754433, + "acc_norm": 0.23809523809523808, + "acc_norm_stderr": 0.021935878081184756 + }, + "hendrycksTest-formal_logic": { + "acc": 0.2857142857142857, + "acc_stderr": 0.04040610178208841, + "acc_norm": 0.2857142857142857, + "acc_norm_stderr": 0.0404061017820884 + }, + "hendrycksTest-global_facts": { + "acc": 0.18, + "acc_stderr": 0.03861229196653694, + "acc_norm": 0.19, + "acc_norm_stderr": 0.039427724440366234 + }, + "hendrycksTest-high_school_biology": { + "acc": 0.20967741935483872, + "acc_stderr": 0.023157879349083522, + "acc_norm": 0.2645161290322581, + "acc_norm_stderr": 0.02509189237885928 + }, + "hendrycksTest-high_school_chemistry": { + "acc": 0.16748768472906403, + "acc_stderr": 0.026273086047535414, + "acc_norm": 0.2413793103448276, + "acc_norm_stderr": 0.03010833071801162 + }, + "hendrycksTest-high_school_computer_science": { + "acc": 0.23, + "acc_stderr": 0.042295258468165044, + "acc_norm": 0.23, + "acc_norm_stderr": 0.04229525846816505 + }, + "hendrycksTest-high_school_european_history": { + "acc": 0.24242424242424243, + "acc_stderr": 0.033464098810559534, + "acc_norm": 0.26666666666666666, + "acc_norm_stderr": 0.03453131801885414 + }, + "hendrycksTest-high_school_geography": { + "acc": 0.20202020202020202, + "acc_stderr": 0.028606204289229872, + "acc_norm": 0.2727272727272727, + "acc_norm_stderr": 0.03173071239071724 + }, + "hendrycksTest-high_school_government_and_politics": { + "acc": 0.18652849740932642, + "acc_stderr": 0.02811209121011748, + "acc_norm": 0.23834196891191708, + "acc_norm_stderr": 0.030748905363909895 + }, + "hendrycksTest-high_school_macroeconomics": { + "acc": 0.2282051282051282, + "acc_stderr": 0.021278393863586282, + "acc_norm": 0.258974358974359, + "acc_norm_stderr": 0.02221110681006166 + }, + "hendrycksTest-high_school_mathematics": { + "acc": 0.2222222222222222, + "acc_stderr": 0.025348097468097838, + "acc_norm": 0.3148148148148148, + "acc_norm_stderr": 0.028317533496066468 + }, + "hendrycksTest-high_school_microeconomics": { + "acc": 0.20588235294117646, + "acc_stderr": 0.026265024608275882, + "acc_norm": 0.29411764705882354, + "acc_norm_stderr": 0.029597329730978093 + }, + "hendrycksTest-high_school_physics": { + "acc": 0.24503311258278146, + "acc_stderr": 0.03511807571804724, + "acc_norm": 0.2119205298013245, + "acc_norm_stderr": 0.033367670865679766 + }, + "hendrycksTest-high_school_psychology": { + "acc": 0.22201834862385322, + "acc_stderr": 0.017818849564796634, + "acc_norm": 0.23486238532110093, + "acc_norm_stderr": 0.018175110510343578 + }, + "hendrycksTest-high_school_statistics": { + "acc": 0.2222222222222222, + "acc_stderr": 0.02835321286686346, + "acc_norm": 0.24537037037037038, + "acc_norm_stderr": 0.029346665094372937 + }, + "hendrycksTest-high_school_us_history": { + "acc": 0.28431372549019607, + "acc_stderr": 0.03166009679399812, + "acc_norm": 0.27941176470588236, + "acc_norm_stderr": 0.031493281045079556 + }, + "hendrycksTest-high_school_world_history": { + "acc": 0.25738396624472576, + "acc_stderr": 0.028458820991460285, + "acc_norm": 0.2742616033755274, + "acc_norm_stderr": 0.029041333510598035 + }, + "hendrycksTest-human_aging": { + "acc": 0.3273542600896861, + "acc_stderr": 0.031493846709941306, + "acc_norm": 0.2645739910313901, + "acc_norm_stderr": 0.029605103217038308 + }, + "hendrycksTest-human_sexuality": { + "acc": 0.31297709923664124, + "acc_stderr": 0.04066962905677697, + "acc_norm": 0.3282442748091603, + "acc_norm_stderr": 0.04118438565806298 + }, + "hendrycksTest-international_law": { + "acc": 0.1652892561983471, + "acc_stderr": 0.03390780612972776, + "acc_norm": 0.4462809917355372, + "acc_norm_stderr": 0.0453793517794788 + }, + "hendrycksTest-jurisprudence": { + "acc": 0.23148148148148148, + "acc_stderr": 0.04077494709252626, + "acc_norm": 0.4074074074074074, + "acc_norm_stderr": 0.047500773411999854 + }, + "hendrycksTest-logical_fallacies": { + "acc": 0.1901840490797546, + "acc_stderr": 0.030833491146281235, + "acc_norm": 0.26380368098159507, + "acc_norm_stderr": 0.03462419931615623 + }, + "hendrycksTest-machine_learning": { + "acc": 0.33035714285714285, + "acc_stderr": 0.044642857142857144, + "acc_norm": 0.21428571428571427, + "acc_norm_stderr": 0.03894641120044792 + }, + "hendrycksTest-management": { + "acc": 0.17475728155339806, + "acc_stderr": 0.037601780060266224, + "acc_norm": 0.23300970873786409, + "acc_norm_stderr": 0.04185832598928315 + }, + "hendrycksTest-marketing": { + "acc": 0.2863247863247863, + "acc_stderr": 0.02961432369045665, + "acc_norm": 0.3162393162393162, + "acc_norm_stderr": 0.030463656747340244 + }, + "hendrycksTest-medical_genetics": { + "acc": 0.31, + "acc_stderr": 0.04648231987117316, + "acc_norm": 0.38, + "acc_norm_stderr": 0.04878317312145633 + }, + "hendrycksTest-miscellaneous": { + "acc": 0.25925925925925924, + "acc_stderr": 0.015671006009339572, + "acc_norm": 0.2515964240102171, + "acc_norm_stderr": 0.01551732236552963 + }, + "hendrycksTest-moral_disputes": { + "acc": 0.2630057803468208, + "acc_stderr": 0.02370309952525817, + "acc_norm": 0.3092485549132948, + "acc_norm_stderr": 0.02488314057007175 + }, + "hendrycksTest-moral_scenarios": { + "acc": 0.24022346368715083, + "acc_stderr": 0.014288343803925293, + "acc_norm": 0.24692737430167597, + "acc_norm_stderr": 0.014422292204808835 + }, + "hendrycksTest-nutrition": { + "acc": 0.24183006535947713, + "acc_stderr": 0.024518195641879334, + "acc_norm": 0.38235294117647056, + "acc_norm_stderr": 0.027826109307283686 + }, + "hendrycksTest-philosophy": { + "acc": 0.20257234726688103, + "acc_stderr": 0.022827317491059682, + "acc_norm": 0.28938906752411575, + "acc_norm_stderr": 0.025755865922632935 + }, + "hendrycksTest-prehistory": { + "acc": 0.21604938271604937, + "acc_stderr": 0.022899162918445803, + "acc_norm": 0.1882716049382716, + "acc_norm_stderr": 0.021751866060815875 + }, + "hendrycksTest-professional_accounting": { + "acc": 0.2375886524822695, + "acc_stderr": 0.025389512552729903, + "acc_norm": 0.24468085106382978, + "acc_norm_stderr": 0.025645553622266726 + }, + "hendrycksTest-professional_law": { + "acc": 0.2561929595827901, + "acc_stderr": 0.011149173153110582, + "acc_norm": 0.28292046936114734, + "acc_norm_stderr": 0.011503891323188976 + }, + "hendrycksTest-professional_medicine": { + "acc": 0.22058823529411764, + "acc_stderr": 0.025187786660227248, + "acc_norm": 0.21323529411764705, + "acc_norm_stderr": 0.024880971512294275 + }, + "hendrycksTest-professional_psychology": { + "acc": 0.24509803921568626, + "acc_stderr": 0.017401816711427667, + "acc_norm": 0.2679738562091503, + "acc_norm_stderr": 0.017917974069594726 + }, + "hendrycksTest-public_relations": { + "acc": 0.24545454545454545, + "acc_stderr": 0.04122066502878285, + "acc_norm": 0.2, + "acc_norm_stderr": 0.03831305140884603 + }, + "hendrycksTest-security_studies": { + "acc": 0.2979591836734694, + "acc_stderr": 0.02927956741106567, + "acc_norm": 0.2571428571428571, + "acc_norm_stderr": 0.02797982353874455 + }, + "hendrycksTest-sociology": { + "acc": 0.31840796019900497, + "acc_stderr": 0.03294118479054095, + "acc_norm": 0.3333333333333333, + "acc_norm_stderr": 0.03333333333333334 + }, + "hendrycksTest-us_foreign_policy": { + "acc": 0.33, + "acc_stderr": 0.04725815626252605, + "acc_norm": 0.33, + "acc_norm_stderr": 0.047258156262526045 + }, + "hendrycksTest-virology": { + "acc": 0.3072289156626506, + "acc_stderr": 0.03591566797824662, + "acc_norm": 0.25903614457831325, + "acc_norm_stderr": 0.03410646614071855 + }, + "hendrycksTest-world_religions": { + "acc": 0.2982456140350877, + "acc_stderr": 0.03508771929824565, + "acc_norm": 0.3684210526315789, + "acc_norm_stderr": 0.036996580176568775 + } + }, + "versions": { + "copa": 0, + "piqa": 0, + "rte": 0, + "winogrande": 0, + "hendrycksTest-abstract_algebra": 0, + "hendrycksTest-anatomy": 0, + "hendrycksTest-astronomy": 0, + "hendrycksTest-business_ethics": 0, + "hendrycksTest-clinical_knowledge": 0, + "hendrycksTest-college_biology": 0, + "hendrycksTest-college_chemistry": 0, + "hendrycksTest-college_computer_science": 0, + "hendrycksTest-college_mathematics": 0, + "hendrycksTest-college_medicine": 0, + "hendrycksTest-college_physics": 0, + "hendrycksTest-computer_security": 0, + "hendrycksTest-conceptual_physics": 0, + "hendrycksTest-econometrics": 0, + "hendrycksTest-electrical_engineering": 0, + "hendrycksTest-elementary_mathematics": 0, + "hendrycksTest-formal_logic": 0, + "hendrycksTest-global_facts": 0, + "hendrycksTest-high_school_biology": 0, + "hendrycksTest-high_school_chemistry": 0, + "hendrycksTest-high_school_computer_science": 0, + "hendrycksTest-high_school_european_history": 0, + "hendrycksTest-high_school_geography": 0, + "hendrycksTest-high_school_government_and_politics": 0, + "hendrycksTest-high_school_macroeconomics": 0, + "hendrycksTest-high_school_mathematics": 0, + "hendrycksTest-high_school_microeconomics": 0, + "hendrycksTest-high_school_physics": 0, + "hendrycksTest-high_school_psychology": 0, + "hendrycksTest-high_school_statistics": 0, + "hendrycksTest-high_school_us_history": 0, + "hendrycksTest-high_school_world_history": 0, + "hendrycksTest-human_aging": 0, + "hendrycksTest-human_sexuality": 0, + "hendrycksTest-international_law": 0, + "hendrycksTest-jurisprudence": 0, + "hendrycksTest-logical_fallacies": 0, + "hendrycksTest-machine_learning": 0, + "hendrycksTest-management": 0, + "hendrycksTest-marketing": 0, + "hendrycksTest-medical_genetics": 0, + "hendrycksTest-miscellaneous": 0, + "hendrycksTest-moral_disputes": 0, + "hendrycksTest-moral_scenarios": 0, + "hendrycksTest-nutrition": 0, + "hendrycksTest-philosophy": 0, + "hendrycksTest-prehistory": 0, + "hendrycksTest-professional_accounting": 0, + "hendrycksTest-professional_law": 0, + "hendrycksTest-professional_medicine": 0, + "hendrycksTest-professional_psychology": 0, + "hendrycksTest-public_relations": 0, + "hendrycksTest-security_studies": 0, + "hendrycksTest-sociology": 0, + "hendrycksTest-us_foreign_policy": 0, + "hendrycksTest-virology": 0, + "hendrycksTest-world_religions": 0 + } +} \ No newline at end of file diff --git a/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-03-10-25-38.csv b/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-03-10-25-38.csv new file mode 100644 index 0000000000000000000000000000000000000000..38627e48f72d4609cb1d678bf4ceee033889a650 --- /dev/null +++ b/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-03-10-25-38.csv @@ -0,0 +1,10 @@ +task,metric,value,err,version +arc_challenge,acc,0.19539249146757678,0.01158690718995291,0 +arc_challenge,acc_norm,0.24573378839590443,0.012581033453730107,0 +arc_easy,acc,0.47895622895622897,0.01025069260202259,0 +arc_easy,acc_norm,0.43013468013468015,0.010159130445178497,0 +boolq,acc,0.5700305810397553,0.008658853690729258,1 +hellaswag,acc,0.31099382593108943,0.004619542392006404,0 +hellaswag,acc_norm,0.35600477992431784,0.004778380758851136,0 +sciq,acc,0.79,0.012886662332274531,0 +sciq,acc_norm,0.712,0.01432694179723156,0 diff --git a/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-03-10-25-38.json b/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-03-10-25-38.json new file mode 100644 index 0000000000000000000000000000000000000000..135159671e70f2f1c34d955d9c6508f9ee62ea6b --- /dev/null +++ b/1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-03-10-25-38.json @@ -0,0 +1,39 @@ +{ + "results": { + "boolq": { + "acc": 0.5700305810397553, + "acc_stderr": 0.008658853690729258 + }, + "hellaswag": { + "acc": 0.31099382593108943, + "acc_stderr": 0.004619542392006404, + "acc_norm": 0.35600477992431784, + "acc_norm_stderr": 0.004778380758851136 + }, + "arc_challenge": { + "acc": 0.19539249146757678, + "acc_stderr": 0.01158690718995291, + "acc_norm": 0.24573378839590443, + "acc_norm_stderr": 0.012581033453730107 + }, + "arc_easy": { + "acc": 0.47895622895622897, + "acc_stderr": 0.01025069260202259, + "acc_norm": 0.43013468013468015, + "acc_norm_stderr": 0.010159130445178497 + }, + "sciq": { + "acc": 0.79, + "acc_stderr": 0.012886662332274531, + "acc_norm": 0.712, + "acc_norm_stderr": 0.01432694179723156 + } + }, + "versions": { + "boolq": 1, + "hellaswag": 0, + "arc_challenge": 0, + "arc_easy": 0, + "sciq": 0 + } +} \ No newline at end of file diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e4747145d381a49ac43a2ac237a1e32dbf9db94 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d294520f89b443e0c1dbf95aa9190033bd9a9e3edffa8282aadd78f4d8608d99 +size 51395415 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5165ac1d155e9b4cd4653664d2e5aec6489ec105 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7ef7b500a66787eee9db13dd2ca2acddd51faff88156819b22a4c9bd808069 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fd3bbd5885058c95a0d09d2d9f626406e30f1a7 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:140186e714667fdcb1e495e27e1685f226884f7f4c2d84421cb56bac90d3a294 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..84bf12d3d6cb814ab3722cf4c1608e79386dee2b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52c1aeda2125129811a5d0ec7eabd3ea1ab926f2a7bcb47aed076b93de04a276 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f88008b7c768107f97b6140852df19174ef8dfe --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c9093b498ba2e9bb98e8a1adc9aff3e852697f47ea2c26b43d5c943f2d1db3 +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ec7d7973f3650ef69b11a13c2b10d0a993fa7ea --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc15255d78cb44ca951211e0bd4ac600054cfaf81f75b211a48b50ebd011c2b +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc686bb67466abba55cfc587bbfa5deae8d71e87 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd80e8ae92d6a31863309a041d9e25d2ded3181970c86b0186cfd34583df159 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77cce023f4f7483c85ca7b71d21ddccc93031e14 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3cc3242143f6fbeab5e26f922cdef749866fe8a3899b56d0febb9b4629b9337 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1af21068807564da8a9980b4bdeb2dcec33a971c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dafa85566d94a757313d19af7faa2a855b25e07b9e6ec51e4f0cd64589087bf +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f20a319eb0f6d1384bb0a6b16656269a1bb5ea58 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:348594104bedc6b6eeba82a559b6cc161bc0dca99a37f77ecf34358e00478a79 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fad1ed7d2127ca5b5af4210f72fcebbc85216b55 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf277af701839d2e470416f08dd16ace9ea796cc98e6e507166e045aaf0eb747 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e667bfa33089e95c6ad5a1be01546a048844245 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b94a3dafba54629c068eefeecf00d05d5ff3a6440b130062551a2752a3551d9 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc3c2c75ff58a7be5937121aa3b5fd274316e2cd --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:164d1aca796a26d12300d7437a254b3b5e9f0d2b5f201510481dbdb2858fab9b +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b835406f323656b84d8f4b504790f8ef117546be --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45a0f3fe500129f06e92ada8836f281406c5648891c3b0391ae7948c3422912c +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..db84c6447df70c0247fc4b6d534bcdabd073177f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86adde93cb07e99a7844fd428f10bfac514e9fda0b387df22eb28efbb12cf6cc +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c201bfa42e3260299903fe473235e6f7f5c5a748 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5d47a791e190435acc4ea2ac0bdcdae527476dfa5f827ae7f0bb3213a7e75b0 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7230b073e653891c29a11cb8651091954a2f074d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e22df623e82a1ebd65cf6643256b557af86653bf0173c6e942709d13d18e1388 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1b0a0839f88016ff65da79b253ab5deb1fa2965 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7828acf17c56bf95bcba492da5e061ad8a35d8db42a78c1a047a11ca1c7cfb94 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd82595863022a966033d0797d97667a02d3fa65 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54aa66977312ecdc2505227db1a42fbed838353f084e6ff9138f0a68b02245db +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7866bf02ebb772e8edafa9cd5bd7063971b3af2a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b730b9da3ec8003fe292d8cc900ff824b4d80de607853ad10046fa6bd9468b14 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..71d26954143f39f414fb6cd3561eca7518baf379 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f399197374a42ac840a9c2721432e7f95497dfe86a6f926da04ac2c28327ba1 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dfb04950e7a3d53372c4d0847a36e50bc856c41c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820ac5f7c61fc6a0007f8bfd86716bc29f012304d9d79dac7995c05ba3f2ac57 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da1b040989c7e156076f1ae19a31faa7bcbea64f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9d380e3a09fee1058fa07ffb30aabf719fba9d291b1e9af495a2ab62028ab7b +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b90cd72518b296351eea182469c2ff15fa2d0345 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a8a85098b0b2411b669575f7d9d11ea99bdb494bd48104c5bb8f7680968b10c +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..866d871cfd2dac063b257dae51321ef4dd8b58fd --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb27c99446acb93dc3f4d2cec7cab831c3739de1e15aeeb0f994ac2b1c0ba75a +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e499a26e883885abbc3538f6fe9ac441ff4b2651 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12d7ce0aae359e4188168f1ae5646c32a0f1ce9d9aac4fc04fe9382d11e4f398 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..96b12ad59b13f0aef4d4608e8e07ee41002fcfa9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50280c8f2b0ffe0e2ab6c2c68aab1608fdaeb501676895f66e813a36f00105c0 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..579b41d4ca3accf09501120e285043c2b16b9d13 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:960a591ed3c00c107b90edfa1ac66c62ce28fc25a90503532b90d95b56853b33 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..79b5aef1fecfee78ce5e1ffb0d28ed63de50bb4a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bf2b314f0fed6a8733e29ee009c8b220e4dccf43fed7f087daac202b7318ee7 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..52133edfdb91d2a7be5e4ec9dec369f7ea26c9b8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0312d6730d1f4b84e9c1632b35330c960ad15ae5e38001274aaa1a15d3bb36 +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fd29edf58c926c11822b43712d157ee9804bd6cb --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc7006d8a5858aabe6c5f4f4edadab0d03a3f50ab4c95f8b1746c564df3d53e3 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff7a7584e0868d44be1f7fbb9a83946f691e99f7 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2442624048be293eb9690834718d6f2081793c454dda59567a05287fd551db0e +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0b533c8c2be20e563d695adfdc39782752f6854 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:728e1964a58af094d1234a652eea5a96c0cd80c7e6eac72e5c644949503c794d +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f80935f853df82884dacc5780c491f52cf2c2d7f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97755dba974da4ef314a2ecdd6783e7b3735b9f81360da33a50aedcba12ff9ae +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a749db9e96030bd326bb805da9cbbbad986a2e35 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99add5a01b34259601a64a70cf75254deed6ed028100b855348667ded7856314 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c8b3bcdd641d12152c999cd27796003ac5df69ea --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a3ed135938c449f46748993f61b834a4f5dbd3fcbd1654ce38113c716cda0c9 +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5366f4caf96cec39900a5d7ff7432d66e44af1da --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43737a0579badc97355c31847d806006321ae03112be4ada39169a87ef8e8d76 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3cb347d0b53154e779b9652c07ddb2f1adc497a3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d0ac6fed95d44a7b9eea4ef454dbef631b8e213e60b46a4efb5489aae79f5b +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..641bd0a7f4bbd72a6736f70aa4f82e03692bea65 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4774fe4d97dc073555dc3552c79e39218e8c990ba1149744cf3d84492573150b +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..12c4c67cad0979d960b7e3ed3bc75e1f313df3f9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3dfeb239207be5742bc301fff04a711542e19c0df721a95c7d4d730a3cd0e89 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..99649fef45ade5d04520fde2389a893767440223 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c64bd3c4938fe4ff8a63669c929d190fec1933163ff933dacf5f252f7d5aad8 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c361fad7f97fec73b194c01c08a0694fe0709b4 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef71134fcfd417959e6f86b01134bc9be67c4c95558a78ad76efced88002849a +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..840897b68ec4bbf62a30eafce7152069e524d24f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c309f359e60685165fab0fcadaf89f2b2f7dc4b203ed9e4d5da5d96033f452bf +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76d8afbdc38ed96a7585de293c85868395613e9c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b38c1e7c59800ead5254ebf7e644fc706154a8d2b86db7b405f9ac7210b350 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7794af14301aab3fe2f3dde01c72bf687c8ebffd --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:737adee632a80bdc4ce4a33018b3a468b672e96104f5f88de390a1e4611061ae +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..06a7d43e809a664a312b1889c5e3de735a155a54 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0643386af8f8ba482305c0aa3764311d0eed4fe8ebb6478d8afe52a0e078913c +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..90a676a677565a3667312edc03c98a95a7a59a1c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df1e65134a05840016753dad053a5a0ece5535fd94c9cef9cc881a94fa21bd0b +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b74b1c2198009f11036629695a173a3830b3ed9e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c65562a99484444b54af60b6255c0448dc8757f4833342449eb6924de58c8b6b +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..310ea4e2598242a317a6818116bf74bca8e5335a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7732e702226bbea8f00fb9aa12d3b4e68624ee128fdd3fffb521528be3f42573 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9934e2f80bfd03d3ee646cca9f52a3bb4ceed98 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7720a85d8a1cd377f0c35dd512ccc8b0a26ec12792d4e9160cbfa1d56d12d7c3 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e524d93d98526262b313dc252f2f035deb00831 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:898dca6a8423cb93dc5d1c9b6a29db205a35456f3b60591e5a447ec544441a20 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c9a4a3d591afc32af29ab1bb88a1c4fa0f9f419f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3839f849027375b5e13d8d58040aeaac1ff15f92684ef9fa1f6abcb1b4a5e5bf +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dad5109d57d501a61cb738f58472dbca11bea15f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80ca3d4aa9e5a077c6cb44bcb325510d9bdfce9c74005213da8c02ef99574835 +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f8407963c38d2f5f6ab5d84d7cc846c35c32f42 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b112ce00eeaa0141a3daae87ec818525502371e827b3e1e43e237c88596d9a7 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..924bccc14c75375eac6797be2d06cfa12229e39b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e80e9dda2593c7a4aa403014fedc158ece922fa780c3d860519dce13826ff7 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a2220d20ea7eafec72049e5b38ba35c38d2c44ba --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:343622fdf0e6db5082b6120ba29a9e560228d9aca17a7f9a91e58598341dafea +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf423d9fdd1ef3c6d4b8ad0c3669158524649b4c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1f0106639fd4a023248fa83fdac70b0285d00957af0918ef6e1c13efc29dd6 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd8e3ffa0fae51169281ecf99a8b8ba8d00d0750 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1ad870d379ffffe11f391017a163c2a07176b32ed2f883a4f8c41022e636f3c +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7471a9cb17369e77b04406f748e1f913f0501cc5 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:131a4dff76f29ad6942deb10d23c040b882c1f85dbe7c94cb5f22ddff0d7c8a6 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be4b542a450da5a2b65c0b608ec5c761004ebcdf --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28a39f1669d172de5962e220386f5a217325317ac0e5aa970a42a7bf6f1578e5 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d9038a47a2d6a1ee3e6ea0674e4fbb036aa368d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417d151ff32e2623a35df7ba9f6a1c256f3f965f02d410b368be58f23738ae8a +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..79a0a3adb1cafd4fdfe2f2808fcd79d6eb8c26a3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb6eea68d2e2551864f5cd13a2f46258ffb6a804b1bfce6a8386ac2e72cc486 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..89b0c1b3cfb93090367504034a466d36be1158dd --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9085953fdfcb0029244c2bba2ab32c100eda83f30b981380edcf8f66ce10860 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7217bc9fb81368f596e428a7db8d6d4f9496e1d0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56cfc24b2c2479044657c2f4b7b0dc3b09c795da7e6dc21751b3959350ea8073 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..42b3b9d47230a2d2b56780f613258e896ae171c5 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff8f988a3800e55a8d87ce8a8f7096eb4e56ec86aba332be4bc69ec54cd72437 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..072a3a51daea96aed6f805351266a700e62aad17 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26af02d7b7ca9bb37f242b4c0d605c5456d37f40dfe96f007ab8858437899a88 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c9893852a607f23481539dea7dceef9df1da2ef --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9e1cbf85fc7c577ce1dce4358a438e983f75275676a91e82380c165954533f6 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c833f03e74bedc2d40cffadbcf511a1455428511 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8233eafcc521205597a6e169359ad758667124b247979a1cc5e608f7fa289e19 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..608956e973b2b25c1d2bae0b9fea70f8e016f285 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96ccc729db3ed5d5bc5e3bc1397709812c043d3580531bc24bad3f1abc2380ae +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78c23344ac71f97f49cd8af316b1397ee9d631cf --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d33304880f0a00af84bb98d92ea4d0581896c8a5ae24fa184f6eb45d5d20688d +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ebb922142c7bd5b32fe79f8a62a938041ba9046c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:364a969407059058d2d1bfaff9140ed11b3322970a51ee4ac71ff848902b22a1 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..422e070ca3f399f179b403472225fb1fa3536f2d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1cb8282cd0c2eb58cf8e75a039822784b96afc59540eeaf233cd1a69156f12d +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b16825cc6b512d825a9a5f80d4b74796e3345f5 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38cfaf3a42f0489a87b626360e01a13a60be9354a92489da55974f37b134aa47 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3821f7e612fdc592c85b1c3d60e6d7ab7e629722 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a43ce6b847688c9f691f4673351e15b2f8c924d577ca7f59657cb266ccbd591e +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..98baa20c8efb1a79a0897c2896dcce83cdce5507 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74573f8dfbede045a239ffe45527bcd67a4d521641fda2134ff736fd160b91a3 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36172a1998b2295ddbca2397cf8aebca92fe42f8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63b034fb10a47b2ef9a4653805a49a548fd79b18d85b70590d4f202072c82dfd +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..71f168b47288cb3e3c634a85576175e5080b4a82 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcb718bc1de15c37cd4307c926ecf2c6591554253d9ed6dc11fadc8bc3783127 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1cb51e81df4b3437c9dc4d7b71debe551c8c933 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd72e79af93815a369c768cc6c3d3fe960a74f03b37510f0ccfdc4b61b76f00d +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..844bf18f3c3065fc7311d4d5c2a643b02b0328f7 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff4198de49a0de5509fa57ce1f73c0bc620d7e11162a4e687be105b18b5ac4f8 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..69cf959f18ac99490c9a2d379140ce4af35afe79 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c8cb1e1d094fca8d588241feda80e3ac72efd2c962de3684cd244587eaed91 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..947b7bac3d8412c20777e047d805edfa5076350c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a56f370c6e4bb90142630ae8ef5383bf413c2be4a5993a9ceda70ea3dd16138b +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..71b83221db607b08c9ad5edcfda2326786434fa2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562dd64a2e6155e1abf51317abd567521d354f9fcbb52a421a56a09cc49008f6 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0104de06b9f29d12f301ed21df1cb84597f23760 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69549a4379b6a4b07a48290023ee378efc3d046eff92b3b0af86f6a14427b90b +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a2e184f0f71d591723b05417fd2302ce60d6b9d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580663e019f6f7a89b1c66c5d64847363b3be72c836b5ca1457ab3452896e2f3 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dbee01c55944b886a00b4a1ea496f71e9d32f4d9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c781ce7aecd787db3374eee1f63dec66e265b115040c1a1630f3dea3b2e9b8 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1571b415ba1cd36b1f74a6da7a4729ffc357ccb7 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc03821ab0d17ada244841bc26e298cd8889a6d38ed816a9e7faa0b154847658 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0faf96327bd654b05ef5aa0673cd2290dbd7ae1 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb37af554fa03b7b50b506a977cddac0ba745ea8d3e4e10c3b49bb5f8c547687 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eff523aa493a7d6124304942f24388a7268cd788 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e4406d5ab3e34c8dc6f6d6a01d971051e6b7d2cfd27c47e5c7e8fb99cd5a177 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50f8a2c28d6ecb3b3603945c82289cba0a7e4855 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b06a0a1af1a9c47d899cc9fa85e6e887e4bf4714630b165af60fae7524c3fb7 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f46f28ef03c9e04b033602d9eb040a57ecd0da34 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:794dc8d1220516a1484b2866c43233ca697dfcbeb2d30d60975e6488b863561c +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..08b0df812bcd94d76902104229ab332159e04260 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65cfbeffd09ea5c351f8fe4449426de997abe2e0c62b9bb104215ddf5a4b9930 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9a5787dd35cf031cf16bafdc12f1f7846dd05e6 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab100d97125edf5a32cc0d16ebfe180759007078f7f508378b9784b51ead0e3c +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e6ad168a4fdcd66c6159ff3051ae604cbe77b42 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e3543f44d9dc92b5b220a05f610a283347468f3efb7e041c598dddc66588d7c +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..64c2c6fc06e5cd5d41d5e9a8d1fe6e0366f1599f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762fe1561dfa2675e91d91edb083b014c02e4485eea94131097ff09a0eeb6a91 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5b2a2ba41a2089e2a8f9a133f2f3dd6e6a68e2c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91bbfb744764cb29c1dae6ffd10020cca228e888303f9c51dac566530959852b +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..56d3002ae8796b770c2deddff1b8708a16bd7f82 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf8b50842bb8c34315532f7e4f9ac055c79a140bfbe293b400e1ec9777f4d67 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17cdff5aa6396a25c2d0425940e538b8e274b9b2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7839f7f2aa1975f32344854d4d6c5de80cbdb381b4c318d06bffac6c8a7f0465 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc4033afa16973dbb909582a8cb91cdaf7b82297 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb86e81e4fc9ca91745c83b491e4a895178582b711388f288ca87fa020cb0346 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76824f3fc403608071284976fe3fce5f9f5ce4ed --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33665bff006a5f1965d104de82ff9f68ce7dedffa5f8ecc16019cb63e936eed0 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cac4aa43bb2c1ae0bf3ef35f1bbe7bc398d1bc89 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:079e570bef4132301bb8278e4b95d985852a992e6c3266c270d1fb25cace6e0f +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c948389127087d1955cd512fed87fb5c21687507 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:685571bb236f4baed8ca0c1ede3d974fd4bd62c287722315c4121e314df8e5c8 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2e3bfc0e4c27992c17bb4266ea8747f3e99ea3e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe3ddc840019a7151f286c11b0ea173996ae2427bb47804ea085a05771b3870 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e3290dcd122ff09871edf48942ec2f7aca6030e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3112bd79da67e6ede70f4345f6c966a05c4b9175b07200ede4af32d8e6634b4e +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4968826ab2a292531402d32462dd179e8e24f32b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f381856457df1781a4ed62f77571a0505f65bb94a8ffe4226f2781a68949ab6d +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..044ffdfc15a22e6907485c3ee7b08336926923f6 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a6de1b22f6892a83de2324f99d0e5746f54efa15fcc485c7bedd3af710ccef +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f67c8772dc72e5fbeaf9c339b7344790cf340243 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:029280c252dccb4a4b0c28781ce7970195de01608309ebfb76a381b896fbc717 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1068955695f644ecb8436be7981128dce686e6a3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63722627a51aa4991ca97099ca4937a47e29b0ed96c6076d3543834860de4765 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e8357c21817dda69b4c3e22865a73a93822a5ab --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49c2da1347a536571150baa625105cd49b5fdb52ab91e21b6c13305e3a453469 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fbcc2b3912c1d5a1ed89bbd1bd35b95f91fbd17 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d54a440c15dc52a3145f46bbdefa7e9bda880bd565fc49be145e8f3df00e4023 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..231469b4e7d2e7c7e4a648a56bc0ed5dedeb802b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0664b36e80241945a3be05fadbb4260599633e81500941e95ba98ea33c4027ba +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d6881feae5af9d13d7ca043378e0bc2fdcf670f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42614549e1ebafe436e6aa10b531a00bc61065bce744e384c3ce12b236977ebb +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3422d105f0102c34b1ea5f473b44a7099d975310 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:475b9ad503a4e53260e057ced319067a49e548d1a7da7b94b7e561bea41516c2 +size 51395415 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd2308ee12ebda7bc06657b6ac8f4714f87d55f7 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f95f3b7128b935630c3c13f7422e0cfb475b7e7a450966a6b8b1e5aae43bcbf +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4250bc33336cdef695ce34b1c64f322153eeb6b2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c82f859cd4049a587307680fc963aa8380cdbc4217986e3e8c0b430d8f87a280 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4db1de0344e190dc59aca36f30ba8f311e9929b8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d29d377638e2bdd529c23ea8de5946ea75452714106b6ff70dc3f0b54348210 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..18f2fdc9ed6a6a22bd3d6f113fc969e09fbe2151 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30aefc644d2ef3c45d4e09de8d8926eb6051f027b3a504ea178a4542f905188d +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ffb3daada2d54472958c2c3e82ca6bd28434a8b3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5c62832c0129b3e1a1fc49114374e06f642dedb91b83a49aa9003554dbb52cc +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f8756ad9644a0861e4e9901fa68dd333bcd40e9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca0a37f5d41858a40d6a5b73749522fc4fbc2f5603550f383f6ef08cf691cda +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f55d50a3bac1144a9f96f5a705231b373f9c76e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:913f45a4eb611cb3dbd1efe912f23e1d7926fdd56fe834eeb3e2edab527c29c1 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..99ede5b3fd0c388a487b5f69c494e67cc070037a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16faac2cf7a8734452ef916b2d66241ac7fcc084b5349021c6cf38c9bc724263 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cac0365e2be7e496a3bf9356b9cc52c3da628d1c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d1c29204828b4c5e649925c1f1c00a25ac4b23720ed194c57926ac45fb02311 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb8e808e10fa638aab37827ae905efbf66e22fbb --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac27a119f2a8e0d39530d6809c5725fc965c7f802f9f4b62f1bd237436b1c4a +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..986323d12eb77f756b7ea7dd4ab2d2cc4a7f5096 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b7e45be6cbe01793b83127ecd00327f4cb138aaa5a3e4780536307fe72354c +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e22f6c05f30a8892f8642b2366437d80fdbc7eaf --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:276d6336e1d8ec42443bd3ced33c085041c4afb5b3977a7e381686c949efe6a1 +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..53dba6590469dddd01d27b1221f52f9ab3ac126f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344688f5dcbb2bf33c5f010a908c316d8c0c08b47c7adb2116bc770b01debdce +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f80a58be8ae6627a174b0c3d949318a7d3918012 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d612a7a0c3afff5c6bd4262574c67f14ef048d70fbd5bcd7551a7940ad260eda +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..949cb4bbbc64ff32508d4333521541c50f8ea00c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8e9e370a66750d6fd809fa149351af20de98c8a41c26b7f7716a3cee77b471 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c5020dc5728c748f86ba1352edd0c3a95cf3a28 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:811f7e5fc60e58f557bcfd3e77492746d1c8b41e879c21031569c35869f2851a +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f79f74d9fb364ee119f995d4d354752393924e08 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b4002288939dcc55f8bc8bb351ca96c09baa3e719088e59ee81e98c64f97922 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d4ed81632e9270a733f90865390ed1d570e21ad --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a94f4769e89ff38ee85b85519a5879bb2bd568ff049b0ce66897bf4326e8588 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..37b3290ad299a79dfe766dc5436c25677af6bb5c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad30dfa645f13c3dcd3b8ba21a3cbad0e46e5d28be4cb8eec7932c7617b8f359 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..72a9f56c592c1edb93ea56d33f554bddd8833aab --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea0271b1b09dab0d33a26ac7d77617d82fc7f69b525741d784564a6157ee304 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..892e820c9ff283f96d263a924815d5e5682558a0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bcfb6a8de650b303fa9d3ca8683c80c5ea63cd519dfca3b73909e488e52b811 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..254b5f1e98e1409786be0de180a14011609ae9ae --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddae1c6e6ee2bc84771fcfc5a693db1be7cccdcf8c723fa47d974e5085255948 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80a04d75f942ae726bb9c00b79b2a739893a142a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f6384a70256b4755020162f961d294936d0da6d4bf08611057c432c461b1162 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c34a8d4a71bad0dda0c3885c0b4cc25226cda3d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae83772092e4db95d937c34a9b828f2e85b705c316a86db6829b3e7c11505ac +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4010e476211048e3b234ca6cf74a96423af2ed65 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e671459bdacd149148750c7e97306bce515287da32562f72efd9c83b00dafa4 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..04673fe1ee93a31ad03e8ff3f60e6028840a0961 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bde4d45f212b35e13f0a51ec82f6ee963080ca81917651db721ec6d26bcce32a +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6742ee4974848f537ef630fbcfe48cbf8439e1d5 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557cbc46a2dec05769fdde85f5510bbefb8310e72cc606eb9eb7517604e80411 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b288dfedcbb8c0ac35ae9251d7fc585f712a5c44 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c39e2ae1abb0ea8ca1a9585298f2582344cb745dac92978bf43e1f76d117fa99 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b581312372c98f1a7703d1587c2cfd0adb8480d1 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c09f2fa91dde3731347abd9685073eee656e237537f60f3342229eac9c1c33 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..42b8dc751f083a98162b6b073cd50b418157f99c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f71b29b0df9674802e486c5fa2895cdd729a722748682d448795cc478ee6244a +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a4561772e927c3f4e800de4ed97c26f769643db --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f6f5831c73e7aafdd528cdcb946b65de19bf7068f9f32d2942239a53e40936 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef5b92362022bd267c4a6314eebbeb6c64ce3702 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47c01705c4a13c4eaa69ac40ed2d6a03048f195d75ac63e7e94f392662d9d255 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c89fb434b3edb406e9e3fe0db37bcd2188d92939 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be58150a3b852474dd0b3e21e25129a3e91c6fa7e8d27f8be5df987a5250e83 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1267d33c28b7151b75291d800a6d550c38f526b4 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10361e4aaf94abc5b1e79d865fd969df1f57db3a252b3430f3d31bf9b608ac89 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f5c154ecef26d7c785691c2203641c55be5eb93 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:482965e0dfe93782e939a66d9042a4fe1f448e2a4db0e64b3d4f8b22ce42d0d4 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..75200e6c28d22bcdec51c2bfc130355d3000dc02 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f351ba2ef42d6a8d414aaf00f19bf28194605ea6a3f622feb4268cbe651779b +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a9271eeaaf3f3f4126bf3f74a07e2bd55b36596 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c35868ad050eed841e293016a70d5de62e95f8f9d6f9e9a389b56c5fde3b74e1 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..86311dcc806f654a6d4929543d6e895857b64148 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a6d19bacbbef8ef9a5c85d8e82ac1eafb61b00e87e4f626a43b30c6776ce854 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8259bf6d15db84fc7935ef681243930175f30306 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:775fb7e4ccdd6c005af159e75b0a4159723603662778ea4c381d78201242e5c1 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..09bcd04a89713a1baffeb1e7047959e72de17f4b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d16ba1de07f5e3bcb34c3641457f8e079b14c8853f92f5a8e3b1850cb9453d +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..429cbe457cfd392ec32a732f7c7a52e8ad1d2b92 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80160dc31cbb8c4bf45d910eb36e97c6cfd6b721c9e57a872fa07cafe15bd134 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da8cc5aa31dfdeb6d69d09c71aca8c729c61cec9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93c7506797964107636a2b0bc493490fe72f0ae69e2b912bd2795c9378117988 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3d9e7280884c097c9db88c073599285ea5e08ea --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0532403b88c8c8df8a40d6771a71f2e90acf2a7c51232df16e8b6bed1f80cf1e +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2b1d898bd5bc46de6080182cc8fe1b649a4d884 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe4616867573a287cf67c5f82380f897a12e87a5436c2be73a6761a4c05a9187 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b02f37bab8e756ca9a82f98f7e19a4940e9619ca --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c6f134a8842da6301cf1318ea5052e44f4acf0b1349688aa6eb4849587d09b4 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c90e8339a24bec9517f8584e49bdddad366880a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53dc0f36dac52bef5653ec20974e01f75bcc653e05a16cb9a139113904f2fbd8 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5407337f57e93dc0d7857e95757080b29f7d66d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15195eee4483c606935ac010e97c9db2dd2d606fab1ba48db9d76bba0077d230 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0146911aa5c3925593cd726dd33a07c4fc884be8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e1c747d06600ff4140e33d16f8de77f4cb07dcf324525b526aea9dfbd92a109 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fdff670c5857c2cfbbafd4bda61b785895008b95 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a527e0bb11fe1362f4cb82d6acbe95ae61f0f01bcbba8428c0d793293ade598a +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa65f122a8b36c90e07a09b2e81ac228c8ce6af3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95aae310cc8d0eb50b9017261baa97dd8ac5e296852c97cf3a7ad09c85f25429 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf129c424464134474e779d0c7a887f151be9938 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcb87f7e747a1f377d16c7dee2c6bd889a95dc6046ac67a270f84ed3556223ef +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f1b937254e4eb60c18fafdc83d883011c661faf0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c279019469b3c39136cb492bc3f104503b587bb5c502f39a6044d83ac1b04d +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7bd1f5650b195ba881bca746a6302b63100000ce --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d8b90d98a08c42fea8a2b94da3a95dd0667bc2dd9efa4600263654c60bd553 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a19e71d3d347f09cefb535b0c525ca549f89e8ad --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b6d867558320b86abc1620b52cd10390b49e000dbaefe83dad233dc8854fb88 +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fee2e4cc2f6e0433199204639c326b0d2d1b0265 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f05126da4480d3ba6356ffd13a6ccbff51f558623d19385017ffe2c37def7230 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..657f772688dabac958e505f303cffbcaec8e42a0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88c73bc16f9ba377f2e3031aedee3035076a4a948045cc9307e9f1366f308e16 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..64a6923d5eb44baf2bdb4c6b810782297cac12db --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac33df5f643aef237d36c976dfb00aee783fb341c8a4f24029cfc0231704554b +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..39bda0d69f2022f3965fc481e8f97be459c6ded2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d804adc66796db0196cad91a73f951647baf8753468caa7e8597b9f66f549a +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..523c5e58590d22c1af76149400f1aa6e6b9ad444 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7730441c13e21fcb9b7db7f3e15f238ba4061eab6b7fc678db0b971a49f38ab9 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..990d1c224145daa6f41357fbf53c2aaf59be8216 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac9c4f97cf75281888f838a4969b604987f6e462fe0a2f722f11a97bba66c7f1 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..06f95f6519c0fb849c63ad585ac1c7f095043e65 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91a814d0eb230a0d81a302215ab86c73c512403e01e78b9cd288c3e9c2e81757 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a53e2301765b1107ee470d7d72fee99d2bf3dbe8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8db1f453bdb4204f406cca732b2db9ba12cdb359899e120bdbbbdac3168c6c +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..35fe59ffc5387d2e71a27f33516ea39c7de61e68 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e47f19c8a43ebf7e5ac51855d43dc745c4eb3c10987c5fac8127bafb218089 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cbf4855de0a3a446bfd618976638940a2936e511 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64ce143f4298735ad8dbeb6995ff1eec7fa5d7aa44f78e24d23f6a05ab8a84d4 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..08d0636305bcca0766ef4cffaec1efab24b6f80b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30fb19024fc9512ebd0245f5954e817123d516e8c6464fc99ea5c1d0bf91b1a7 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77a9bc0c2e7093cb6e989d8f79714c370ef12f65 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08483121270a664f895e6cd33aa80cc3c786c99f42e13eccbc938b3a3c3b8ff8 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b370e1ee9a1907323a673b9071d186aefc08133c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084f7030bed12dbb48685727028fc62dfc53d479e800b4198e0c92e11f30f194 +size 51395351 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7ab44c62af25ffc8f4c2314d653e2c052b78485 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03ed70a6e9b4ca32f8ce2c36a523d8c85138bbcf6a50a9ac3512dbec0daa029d +size 51395554 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d32a420a5cd3225c4f712640130075a2154eff5c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0245681fe540904810bb914d97073bc205efa37d95ffb660f09ce77e46f3fab1 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8131ae15b4586c557fb2b6311041cf660a7bb15d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:176e2075106f7b226db85ab429b590ad40521e3f97a21677510e977bc486e867 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..abea35e7992d30fdb21b18d0ce08e575e5d68ffa --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c8ed2656f7c25a0dd43dca7612f1262edf6845f0f7974cd0ce8c56ecf03019 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..721b0e4c7e491053cc3d6040b8fbd5b74f1e5dbf --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76aa628c236d32d2f519b30b3bc30b724c5e3ef2bb29b2b33de9c96d2bf5c610 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6d34db06730f0e9630da7b16dc8b6551904ed1f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b7bd34bd40b215690e3347e49039d854fea96167c5a3848fa94ccb870ffa49 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ca309bd98b100c2623f34db26be3c8fb6e71755 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36b38921b827bbe02943a588eff4353f6fce5c77ba1402eefeb67d248f32f243 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4cfb45c487b2f7dd96a6c9b4dab8318c2b041bd8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ab9b61fb517101f74ab044c02728f8823097fb729a3bbd3db4df93082c5b31 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..49d40becdb9ee1b4aa23dc5c453502e135c03197 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85e52de619f962af1f1e9386b454836519b66afce241214749a413db7bce68f6 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..018bd5aa0354e805d8a822b3c57137931752a7ab --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d083945c8d347c1fe62fcf6568dab8f59c7e84f37b4d8fc9d94d0e2d264545 +size 51395554 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0eb98bedc1d3a2a92b7ac3e0dc6cfc7acdc09ea --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd78fc1b46b13412a918685cca21517eaa7fc67fcc114d0fcdc63d2d0100507e +size 51395415 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b2727768e6dbdc1affd10db142fd2bc04aba7b8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa60bcc1c29a276c61c05b1f085ef0660a845cae9d705d3f3cd4d699ffb71223 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..079125186aa665e771b2411b86572eabdd776f35 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cb682eee82b8127b89f78b7b40fec8c688c5d60dd5a614b4198323f5ff56ca6 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..58e751488e7d32903fb684081e803023a7779d8e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7267bed7189e07481f5ac4e47c376acf5b50ce11ead9b7312c9a2956035bab5 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36745e604be992f74fc1f0677faa222f074528e3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fd3fa980f47517d6739bde9e714b7b15deaaa377761ff5ac759e94dff3a7a8d +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..15aea94faa134396969970dd38346f36fd942d75 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7f13439ef74adb46528ca3fee5783dee4b72d36e3dde7e5f35481da08efd8f +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..45a4d8b551ae2c5d4f61b0cd1787a1ab965024fd --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:013cf25cf02bf29feeadb00db8e794fe8f29c9accd4ffbd21ff5b2aa6dd34fa9 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ccf0db339c5d9e576f884cb7c2f9f36826c922ca --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dd28027520ebcda858f042cab9c244d0f0ffcbfc28aa4952445c212572ad36e +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c5f5219a7752a15d206869d844358f36b2941c4 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dea40ab98451ee29f95bffdbd441b296ea43a01a5af321fee9c883e40c1b2be +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..242c04fddf27a2abde7123425ccff8f4f720c166 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:395e4268a98c25d7aad0524a111f3691ba69cbf733c89188b7300abefbd3c85e +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..48f02416c6b411a96d66a05423f8c5ea887925c8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d56bf92de7acbffd7e2af12e25e565bf990c1922e3c5b1c47cdae69e75f41d95 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3534f46b381fc4fe466a947d93705a6b248aefa1 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca23a6a7a3cac13bb3caaf809ed2f6fe122a0123472ff6cd17ea4b0269167f25 +size 51395415 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b432d4cbd74cd1180f6501c2ef702e0e66e8cb86 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b16fa100d817ad654b81e551569072cbb35d25701586d8fae923a8e5936efdf8 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..399a998822235871aa4b4dc6ab8d8df4cf67ef69 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17f5e2e57293e1ef12a5d5edafba0e539b628f6a69f53535b3fc3cb96baaae8f +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..15ab112d6c14c65c76442598d07791aae72f99dc --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd234fc359db3c78bc99782c97cbb2663d8e65264a102c4bbb0a39e556bf8c12 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7043b5523faae2be31806fd4d2a42de6cac64488 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc135966de3057330a68088ed399b68b14c9aadd5cfe6e4c28d11f159f6d897 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c6e763bb7ff1b08b28b92b7f17c8b4fc95820d3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90b3e66914926b361393ed3a62ae319d11fbcec1ecf2857b4c214d435cc5e183 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..723e75891fdf930f24846c6ce6c959aecf2b2b93 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6bf6572593ed24d8ce84f121f47538bdb55ae7544166d10210f49b599df452d +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..942abf5d99045c48a3ba6086c2317d2747c86204 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1689b6d4dcf69f4a258aae10704740a1f64582853f31634788e92072f9f5b19 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..df3bc2eeda5bb32c6c55a16e43a81148ba499495 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c28b06c72a8854e7932f831ee58c2094b75b3934ccaf0074646def1e0375cbdb +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e64bb3c78b223ed59d47fa07039a7316c7443339 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:914ace680b7776613dadac08b3c7812cef407de3954e4e989ea20bbf64092ee4 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d51ac0bbf1a97bd5c1165337cefc0f3216643b2f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41c3160b7d358ee9af7176685e52caae6f75e9e668d31e8ba7e64e895e9a39ab +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f2fad6355fff68ff3ba9d58d7cecb7bf11cf442 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:060a14d86007332c3f5d561a7d4f6d90c8f5ef3f09681850d53ed01c148308b0 +size 51395415 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..58466fe5680b093d02a9507d2ca0c77ad8ce954d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74687976b9e890b08bc444fcbec8d932a977c938b42d44c7c655591ba91db8ec +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..24447200d2c3154440fb6cd85d47186286581120 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbf50a08146279a6d494845b04b4a26215a533aa6963f42d9537488166f6d9e +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c9d8e61b667385260a5aff74af7c6bc29cb97e7 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dac8af2cccd2b14e5ae1434eff24249d6e024984fa63c8b51e261f5787f6d6b +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85cf8d771f2f7d70e582925bc95da70d51a43e6a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff802c4c47f908b3f00cb8e744a3b02e6078a2eb39cdb9429ce771930091b20 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..decfe9d55b99556a99be958bad8309cc22d200c3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64be0f78f9cce996635636e5ff618c8c6fb34bddd352553de9928fda5dfe28cb +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..229752758d45db742f6d09db99198171f82dafba --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8beeea18b054347e3034f620cfc456d07560b02a8149363f34f725261fac6f16 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e7fcde9b8dd7f8782bd8f2eb3ed2dcf4012fef3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43e15d33fad019dd85aca9cc8c4c1662cf04eeb53c8e99463e2978b2dfd3d444 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..886f6acb8486f4da194d2d9ee37023f5fed61959 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81f6d9f0c9695231a42cd826aa9b5a1152973345adee70c12887bf51dc2f012b +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8088038eb09406c39065670b30b0ba2a309aaae --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9ef187d737ef39267629b69d1382b52ff677d032b272750f719bd439df94f1 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf595bc602eb01bf56062f2074b25715a6643a66 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ca12dda604ec7088acccb0cc0864c1cb576c7836511ec550a6cb819e1d9bf7 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34bef844482f658f4c8fc8f416c80db0a807adb2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4ad91bb453af3b04943811ca8a7cd5dec37c7c6506ce85c866e6e895321b6d +size 51395479 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9bef07492fa959c1facc16ab5c0156f899b15c91 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc64665ec552b2e6f12429646ff67b4013e24ba31f1b7be58db1952e40063a4 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd42eec81318dce90e0bbcd410c6749f15733d63 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae568956864298696f11b95a8c1175d1e428c6129a80d798457f6a19868f28d0 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f25e005855cb26ab2bd87525a18c770f0ab1d48f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:317bf6a5929e614bea058caf4ead31475ff593a03cba87abc497afb59db5336b +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d9bcd087d985d469b7947ad18a9fc78c5434c195 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d1a593195611232a88a68a52b3499e47359298c2579bacdbc46f74432ca1d7 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e0568c3dec1546114b72f3bd531b51d6f861031 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:764b0d867d69e54cb8c448a5d6a4ca533afae89805d108cd64226ff1f27baabc +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87c1dd3e795fc70ded40fb6488855f758d26f7fd --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d95c778340ef23ff29631fdbcee1bd2a89dc23bf3c68988adc860d142b1bde23 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..70929a10e50f45338fa82bbf111f6e92203332ec --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d83b089b3360bf596f56f69428579f8ded7f695ff5b754cf5a8ebbfb56c24d98 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1cefb4267210918cae47a95a736bd8d732177cc --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:998d395cec3d34c3f83a354bcd3ff1f0ffca9edb0197f64ec912dab4928e1a22 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cc9c33e1cff02668cb3c912adbdf0bfd0fefe4ed --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2f49c3b5211b043fdbc6b4ab83508d7a1a8ece536739fdb2040d67fc9b3c0be +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d774effc0686db137dd6bf0523445009514f650 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23418981cdde7a8c3918cf56e156b85d41f5017b3a6acb903c894ba299131827 +size 51395554 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9632d7718f17d993ee27c62e9a718fedf09a18c6 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083832e4f92a79d4aedd18375eb885b26a630084a670db494efe931a7b3c412b +size 51395351 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..54170483a09de5b85b0a46e425299ef0235238ba --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12a276dbb73623b2a1b3d623241d71410d21eb987841637ce99d0e124c34658 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd48ef11c85b60dd26e36232868345f9fb701fa1 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09a63d4ba9af980e8797f535bfc8a6a19c8fa7b75f3aaebe3637caf846163a10 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8c400486891bb8a56bf9368c951a6c49b6d3cac --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4142fea50322870eae56133d534c8c585bf36948f3ba41d9ca62594210a45ab +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..790d4df9edfec97c310365d46732cf8c4ff7b2c4 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cadc1339b1eba83735ba7bbc081df0c9b7a217b8f8644abad26e501911d683d3 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..855e728eddfe85665e22278bfa542dadb0a81d0c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b52db6f8dcde36b39ed352a5f826746c2095670038801035001e1767693c03d +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31b85a161bfb0b724568d4be7c9aa04910665c38 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d2981a3c9b55fb02a8989d34aaa87938b7faa69524c388bbf4f5ac84665661 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..71a045d6174ccf7bee05af2d4de5a5588e5af8d1 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ae483d1542b3858b430ffa330488a8425baea1b3e870a12e8ba48e37ed40b2 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6038b1e049fce5224e0cf1e6313b5536c045dae6 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b136cad79f02a7f50d448bae280fa2ac8dce79505e7e4d2ac43d6ac50f05b2 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d5b2c8a01f164b8550de0be68ae21765db80c3f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9939d2a87cdcf53706cb81793b49f5086cf68bb41fcb84ac0f98e6c009a4ab74 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c75028b0356f4920be17018e25eae5932759704 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a914997aa5e4fe798f6c95716dcc3f1feac44fee8fb92842a005cceba300aba +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9af340863a25b0eebe05620c213ee8d86195c8f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa85c3e65ccf4c447a819255f40a719d1502df134a1e9469b4ba12b479a50b65 +size 51395351 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cc123e274236a617e414ea77c778f50ddad7a4b0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59635c897b7b8c6399f3b641c07d108231692de785613a802d0358f8612ade19 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..35e4e2af53f57efc68ba7c141559c07b03b6a623 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0195dc1f38aa24154fcfc51e13d3cf16cf0cea94bb204191b90ac24e1ce216 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0cdae06070ce28d2d36aa9e1f3823d4306ff3934 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02478e8b44e6f56e62a6919b5c6fb412481a21d155df954208c2f910a5675508 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e270afab676c58f6f9375dd1bb7ce97ff78ff57 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d83b6d8952a47b845ac1f2c7a692b9deff622190f0bf5b7743fa39eb477ae78 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..49a5a4ffec54d235dcaff6e0fe9d165622fe055d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997f1ad00201cc1e435605758d416ffc1aef264ad799a4a40a39384a3dd5e955 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..22720101fb345f7b5d6958d91b7a15fc34c690c2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:303af2ba32251991372316509965560ecb06d7f407d9a295c392414e93915b93 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d5d912fcbe41b90fc6d3c41547be42f102362d3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ec9c9cf3dc5ab500e4b32568f7ecbba9ff4017ebc4b3200ee2feab576f72f4 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..140079887b21febbdd3685a96385bb0bbb544dab --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aacfa7938c9f982c654eb4690503f72a271b5a3a7b7165db81f07204aa8afcca +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1c97070fc3a94093027af5fe23abf9e349a75b01 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c944d309390867b8d29bedce26f6115c59685f4ba3f4433ab4ef556505448667 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c19b5825ce46cadfb5d51feff165d5ea32943344 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d35da93df0ec9c1ef0993ae6098916335ab7ec4517ebf4b1c91e502c1ea121 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b0548e04cffd5003cf83e1471864aabc8cd5a4d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4438ec224162cfd5f956d2269d155ad971813c2a5439bfa3483c598c1dd259c9 +size 51395479 diff --git a/1b121b21b/global_step39672/layer_01-model_00-model_states.pt b/1b121b21b/global_step39672/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce0afecb3aa74a4e001f2482f36c1581ed699627 --- /dev/null +++ b/1b121b21b/global_step39672/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02668f8327c6c269c9737142c593d2cdf7e733a3e8978e3aae4312d0ae6909d5 +size 187630851 diff --git a/1b121b21b/global_step39672/layer_03-model_00-model_states.pt b/1b121b21b/global_step39672/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..47d9fc71d8c98cc26b402a3636cf049b03144641 --- /dev/null +++ b/1b121b21b/global_step39672/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1a26ed3139996c37802107d89bc1b01b2f38c048e2de6453c7a6ea743eb2c8 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_04-model_00-model_states.pt b/1b121b21b/global_step39672/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e53087c44acd3e49e26d99f0ce9f838c1508a8aa --- /dev/null +++ b/1b121b21b/global_step39672/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:455d109fab23f554103451325b083d7828072e1eb37f00c255fb8ffd988f87ef +size 77121283 diff --git a/1b121b21b/global_step39672/layer_05-model_00-model_states.pt b/1b121b21b/global_step39672/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a0841f27541946e689a17af0d8998225680c655e --- /dev/null +++ b/1b121b21b/global_step39672/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e250514cdc93789e8b6bc9e9be6e3d20bb07b9802352c1528ba9bff5b9a76d4b +size 77121283 diff --git a/1b121b21b/global_step39672/layer_06-model_00-model_states.pt b/1b121b21b/global_step39672/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8980166fc77b3a622326fa5a6ed76bd4da6846d --- /dev/null +++ b/1b121b21b/global_step39672/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db4e8c5335b7f20749412ca18a8d4b8fe23e3872c43f4a2f0d3c938b74e671f8 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_07-model_00-model_states.pt b/1b121b21b/global_step39672/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..29ad3f1d9948c7676b08509c7bdeb342684e840d --- /dev/null +++ b/1b121b21b/global_step39672/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54431163f7dd601f53fb8e852120dfbdfa8271eefbb3cd89cc6c30d6acf9bede +size 77121283 diff --git a/1b121b21b/global_step39672/layer_08-model_00-model_states.pt b/1b121b21b/global_step39672/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2cda9203647bf10917b72b5ba6af14aef2c3e0da --- /dev/null +++ b/1b121b21b/global_step39672/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:929719eed034470037ddfb7f2358dfd58b267a945cecbccce73eebd4e9cd623f +size 77121283 diff --git a/1b121b21b/global_step39672/layer_09-model_00-model_states.pt b/1b121b21b/global_step39672/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e12edd3d062f97ba6281503cbe113401b11bc2bc --- /dev/null +++ b/1b121b21b/global_step39672/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e1bf4ff3713c2dd41bbc8f69a387f7e87b5e45783915e0212608b92b6ad2df +size 77121283 diff --git a/1b121b21b/global_step39672/layer_10-model_00-model_states.pt b/1b121b21b/global_step39672/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2af7ee5dae5dec4d48efed09e46f00885600d3d --- /dev/null +++ b/1b121b21b/global_step39672/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2facc78bf9a0483d288005679406037e62a7a537f7659c931530ff375c81f9b9 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_11-model_00-model_states.pt b/1b121b21b/global_step39672/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b91c48925dce6c2ab8327ccddbc3eb5059087bf --- /dev/null +++ b/1b121b21b/global_step39672/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d768a586a1aef0b1006260ba6979ae8e4a7f235f4171448cceaba19c29251d7c +size 77121283 diff --git a/1b121b21b/global_step39672/layer_12-model_00-model_states.pt b/1b121b21b/global_step39672/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0002466486880cf33e16a142b2820ef034fb5197 --- /dev/null +++ b/1b121b21b/global_step39672/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc0750cd16331cb53130890e7d81ace5382f7818c0e47be931bbc7c9fb83cc83 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_13-model_00-model_states.pt b/1b121b21b/global_step39672/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae252e77a6090db910eefb2d18e90765f390ea9b --- /dev/null +++ b/1b121b21b/global_step39672/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe183ab22b3081ff6a0fe54ee1d5bdf65f451faf9a690062dd82546b6a8a8e7 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_14-model_00-model_states.pt b/1b121b21b/global_step39672/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dba741c59eeb02263107cc12443a13566de59bc7 --- /dev/null +++ b/1b121b21b/global_step39672/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea314eadf5bb7191e1fd46e38832aef4894af565a064bc0eb5cd153a33da826 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_15-model_00-model_states.pt b/1b121b21b/global_step39672/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d43828c1d544b4ab33eededb13be30bc8febb812 --- /dev/null +++ b/1b121b21b/global_step39672/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ace3b9b2413cbff22488911ad7ca2d4bb2636aef83c3c314be645e1c00afb1a +size 77121283 diff --git a/1b121b21b/global_step39672/layer_16-model_00-model_states.pt b/1b121b21b/global_step39672/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4570cb78c36ff57d804bdc194ffae25fa3d3c0ff --- /dev/null +++ b/1b121b21b/global_step39672/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f31fb95bdac382e031e02a1da581152dc46f6ef414ad3b47298e963b90f47ea3 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_17-model_00-model_states.pt b/1b121b21b/global_step39672/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fff6fab5c676367ad404920b4d3797b2e92be235 --- /dev/null +++ b/1b121b21b/global_step39672/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:620c7b26c96a129928a6a7d1f7017eb2f7f604d6bada15cf0a1827799a39f1f8 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_18-model_00-model_states.pt b/1b121b21b/global_step39672/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..20ad0c3ec0cc4421e5940b76e1ae8baec92ac516 --- /dev/null +++ b/1b121b21b/global_step39672/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c23e7114ee6f77baa53fe90bf67bdfc87391facd71b8d3f0ee45e1fd51a22fa9 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_19-model_00-model_states.pt b/1b121b21b/global_step39672/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d118f14cd4f9acd094a265389c942f8afa78be8 --- /dev/null +++ b/1b121b21b/global_step39672/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67c764de0c45f655220a326fbe6d47467c52f5bec9cda652f0c6c563f880215e +size 77121283 diff --git a/1b121b21b/global_step39672/layer_20-model_00-model_states.pt b/1b121b21b/global_step39672/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce4554039d0089f1e0228b29ee5046f578d69f43 --- /dev/null +++ b/1b121b21b/global_step39672/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc93d1579050faf15b4f73498e15ba9e60ad70276dab59389f6f428cc1876b04 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_21-model_00-model_states.pt b/1b121b21b/global_step39672/layer_21-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a61fedbcfab0386a4e5655c672430932a4d5381a --- /dev/null +++ b/1b121b21b/global_step39672/layer_21-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9206efe08a94a342f0c16508380bab9d104f0bc7e4dbd29318a44af2d701e14a +size 77121283 diff --git a/1b121b21b/global_step39672/layer_22-model_00-model_states.pt b/1b121b21b/global_step39672/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..986954856148d5365ed6b097834b1307e9da2bae --- /dev/null +++ b/1b121b21b/global_step39672/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dd4ff6711a2ca1474231a93ab9a7742fc78aae9f6984f99747b99e71021f595 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_23-model_00-model_states.pt b/1b121b21b/global_step39672/layer_23-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fea2cf1c102242e4a82b0975ab2f6f41ec342291 --- /dev/null +++ b/1b121b21b/global_step39672/layer_23-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ad82bab7d44df6ad8316174dfc5469b73bbb3225272eee195ff70ae71b7556 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_24-model_00-model_states.pt b/1b121b21b/global_step39672/layer_24-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ccc3f5702a0da399c54833734374f664ffee95f4 --- /dev/null +++ b/1b121b21b/global_step39672/layer_24-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92461c9eeed4bb3950bea4488be4268c8985fcc3903b8663c536b4bdd31bba82 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_25-model_00-model_states.pt b/1b121b21b/global_step39672/layer_25-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d812ebd4439483263a7d61bb348b06758659637 --- /dev/null +++ b/1b121b21b/global_step39672/layer_25-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3f819474b4b7ae491c0a997b4bd64a32280e802a11e8da7e404e62a143d6e68 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_26-model_00-model_states.pt b/1b121b21b/global_step39672/layer_26-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dafadbc342485f7cf987069a92f76dac8759d61d --- /dev/null +++ b/1b121b21b/global_step39672/layer_26-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e878014f7619697e5ccfa247609d054321d72546f28f43ed021f5892d61bf2 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_27-model_00-model_states.pt b/1b121b21b/global_step39672/layer_27-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..52d81df223755e91fbd22d17e931b63414ac2194 --- /dev/null +++ b/1b121b21b/global_step39672/layer_27-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c61ffd891998967603641d0c8fd4d305763de8e4cf7685bc52624a781b1c26 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_28-model_00-model_states.pt b/1b121b21b/global_step39672/layer_28-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fdaf0c58c01ddcd9d96bc9e4de8bbfadcc6d168 --- /dev/null +++ b/1b121b21b/global_step39672/layer_28-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1630dc36393ae1b7d2c453797dc33fc39ee649e6b4135a21c371dbe2a94b3026 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_30-model_00-model_states.pt b/1b121b21b/global_step39672/layer_30-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2cf6de9c2b61568011408c05f188bf4471eeba87 --- /dev/null +++ b/1b121b21b/global_step39672/layer_30-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aaef67f37af5578ed5ebda875c399ba52ed245b56c1749c70b3ad92a9341871 +size 8387 diff --git a/1b121b21b/global_step39672/mp_rank_00_model_states.pt b/1b121b21b/global_step39672/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a9f60f4c71821f513e46d3047bd8dbc45d69933 --- /dev/null +++ b/1b121b21b/global_step39672/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8338b86e558d097074025ad55ed2adf4d3327adf57aa1968347f90ac71dd0a8 +size 43507 diff --git a/1b121b21b/launch.sh b/1b121b21b/launch.sh new file mode 100755 index 0000000000000000000000000000000000000000..6c3445845a5dae614feb4b8a1206322cd7bd9050 --- /dev/null +++ b/1b121b21b/launch.sh @@ -0,0 +1,53 @@ +#!/bin/bash + +# Launch script using torch.distributed.run(). Used by slurm +# scripts, don't invoke directly. + +# Samuel's fix for apparent error in SLURM initialization +if [ $SLURM_LOCALID -eq 0 ]; then + rm -rf /dev/shm/* + rocm-smi || true +else + sleep 2 +fi + +export NCCL_SOCKET_IFNAME=hsn0,hsn1,hsn2,hsn3 +export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK +export FI_CXI_DEFAULT_CQ_SIZE=131072 + +# debugging (noisy) +#export NCCL_DEBUG=INFO +#export RCCL_KERNEL_COLL_TRACE_ENABLE=1 +#export NCCL_DEBUG_SUBSYS=INIT,COLL + +module --quiet purge +module load cray-python + +module load CrayEnv +module load PrgEnv-cray/8.3.3 +module load craype-accel-amd-gfx90a +module load cray-python + +module use /pfs/lustrep2/projappl/project_462000125/samantao-public/mymodules +module load suse-repo-deps/sam-default +module load rocm/sam-5.2.3.lua +module load rccl/sam-develop.lua +module load aws-ofi-rccl/sam-default.lua + +source venv/bin/activate + +MASTER_NODE=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1) +MASTER_PORT=9999 + +echo "Launching on $SLURMD_NODENAME ($SLURM_PROCID/$SLURM_JOB_NUM_NODES)," \ + "master $MASTER_NODE port $MASTER_PORT," \ + "GPUs $SLURM_GPUS_ON_NODE," \ + "CUDA: $(python -c 'import torch; print(torch.cuda.is_available())')" + +python -u -m torch.distributed.run \ + --nnodes $SLURM_JOB_NUM_NODES \ + --nproc_per_node $SLURM_GPUS_ON_NODE \ + --node_rank=$SLURM_PROCID \ + --master_addr $MASTER_NODE \ + --master_port $MASTER_PORT \ + "$@" diff --git a/1b121b21b/logs/2088000.err b/1b121b21b/logs/2088000.err new file mode 100644 index 0000000000000000000000000000000000000000..efc203ead529e045f5a23c56a4442abc531a4e53 --- /dev/null +++ b/1b121b21b/logs/2088000.err @@ -0,0 +1,1830 @@ + 0: Successfully preprocessed all matching files. + 0: Detected CUDA files, patching ldflags + 0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... + 0: Building extension module scaled_upper_triang_masked_softmax_cuda... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module scaled_upper_triang_masked_softmax_cuda... + 0: Successfully preprocessed all matching files. + 0: Detected CUDA files, patching ldflags + 0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... + 0: Building extension module scaled_masked_softmax_cuda... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module scaled_masked_softmax_cuda... + 0: Successfully preprocessed all matching files. + 0: Detected CUDA files, patching ldflags + 0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... + 0: Building extension module fused_mix_prec_layer_norm_cuda... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module fused_mix_prec_layer_norm_cuda... + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. +18: Successfully preprocessed all matching files. +16: Successfully preprocessed all matching files. +22: Successfully preprocessed all matching files. +25: Successfully preprocessed all matching files. +12: Successfully preprocessed all matching files. +23: Successfully preprocessed all matching files. +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... + 0: Building extension module utils... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module utils... +24: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: + 1: + 1: + 1: + 1: + 1: + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: + 2: + 2: + 2: + 2: + 2: + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: + 3: + 3: + 3: + 3: + 3: + 3: + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: + 4: + 4: + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: + 5: + 5: + 5: + 5: + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: + 6: + 6: + 6: + 6: + 6: + 6: +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: + 8: + 8: + 8: + 8: +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: + 9: + 9: + 9: + 9: +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: +12: +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: +10: +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: +10: +10: + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: + 7: + 7: + 7: +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: +14: +14: +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +15: +15: +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +15: +15: +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +17: +17: +17: +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: +19: +19: +19: +19: +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +20: +20: +20: +20: +20: +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: +24: +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: +21: +21: +21: +21: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +25: +25: +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: +26: +26: +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: +26: +26: +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: +27: +27: +27: +27: +27: +27: +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: +30: +30: +30: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: +31: +31: +31: +31: +31: +31: + 0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... + 0: Building extension module utils... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... +16: Loading extension module utils... + 7: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +14: Loading extension module utils... +18: Loading extension module utils... +14: Loading extension module utils... +18: Loading extension module utils... +14: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +14: Loading extension module utils... +18: Loading extension module utils... +14: Loading extension module utils... +18: Loading extension module utils... +14: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +17: Loading extension module utils... +15: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +22: Loading extension module utils... +22: Loading extension module utils... +19: Loading extension module utils... +22: Loading extension module utils... +19: Loading extension module utils... +22: Loading extension module utils... +19: Loading extension module utils... +19: Loading extension module utils... +22: Loading extension module utils... +19: Loading extension module utils... +22: Loading extension module utils... +19: Loading extension module utils... +23: Loading extension module utils... +22: Loading extension module utils... +19: Loading extension module utils... +20: Loading extension module utils... +23: Loading extension module utils... +24: Loading extension module utils... +22: Loading extension module utils... +19: Loading extension module utils... +20: Loading extension module utils... +23: Loading extension module utils... +24: Loading extension module utils... +20: Loading extension module utils... +23: Loading extension module utils... +24: Loading extension module utils... +20: Loading extension module utils... +23: Loading extension module utils... +24: Loading extension module utils... +20: Loading extension module utils... +23: Loading extension module utils... +24: Loading extension module utils... +20: Loading extension module utils... +23: Loading extension module utils... +24: Loading extension module utils... +20: Loading extension module utils... +23: Loading extension module utils... +20: Loading extension module utils... +24: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +13: Loading extension module utils... +11: Loading extension module utils... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: + 9: + 9: + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 9: + 9: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...Loading extension module utils... + 9: + 9: + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils...Loading extension module utils... + 0: + 0: Loading extension module utils... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +20: +20: +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +20: +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: +12: +12: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +10: +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: +12: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +12: +12: Loading extension module utils... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +18: +18: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +14: +14: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: +14: +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Loading extension module utils... +21: +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Loading extension module utils... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Loading extension module utils... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +21: +21: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +23: +23: Loading extension module utils...Loading extension module utils... +23: + 2: Loading extension module utils... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +23: +23: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... + 1: Loading extension module utils... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Loading extension module utils... + 1: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +21: +21: Loading extension module utils... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +16: +16: Loading extension module utils... +15: +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... +21: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +21: +21: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +16: + 1: Loading extension module utils... +16: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +16: +16: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... + 1: Loading extension module utils... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Loading extension module utils... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +13: +13: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...Loading extension module utils... +13: +13: +13: Loading extension module utils... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +15: +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +15: +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +15: +13: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +13: +13: +13: Loading extension module utils...Loading extension module utils...Loading extension module utils... +13: +13: +15: Loading extension module utils... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... + 4: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: +19: +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: No modifications detected for re-loaded extension module utils, skipping build step... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +17: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: +22: +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... + 4: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +25: +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +25: +25: Loading extension module utils... + 5: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... + 4: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +24: +24: Loading extension module utils...Loading extension module utils... +24: +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +24: +24: Loading extension module utils... + 5: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +24: +24: Loading extension module utils... +24: Loading extension module utils... + 5: Loading extension module utils... + 4: Loading extension module utils... + 3: Loading extension module utils... +19: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +19: +19: Loading extension module utils...Loading extension module utils... +19: +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... + 5: Loading extension module utils... + 4: Loading extension module utils... + 3: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +19: +19: Loading extension module utils... + 5: Loading extension module utils... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: Loading extension module utils... + 3: Loading extension module utils... +22: Loading extension module utils... + 4: Loading extension module utils... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: Loading extension module utils... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: Loading extension module utils... + 5: Loading extension module utils... + 4: Loading extension module utils... + 3: Loading extension module utils... + 5: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +22: +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: Loading extension module utils... +22: Loading extension module utils... + 3: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... +22: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... +22: Loading extension module utils... + 3: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... + 6: Loading extension module utils... + 3: Loading extension module utils... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Loading extension module utils... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Loading extension module utils... + 6: Loading extension module utils... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Loading extension module utils... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Loading extension module utils... +11: Loading extension module utils... +11: Loading extension module utils... + 6: Loading extension module utils... +11: Loading extension module utils... + 6: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +11: Loading extension module utils... + 6: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +11: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +27: +27: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...Loading extension module utils... +27: +27: +11: Loading extension module utils... +27: Loading extension module utils... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +26: +26: Loading extension module utils...Loading extension module utils... +26: + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Loading extension module utils... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Loading extension module utils... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Loading extension module utils... + 8: Loading extension module utils... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: + 8: Loading extension module utils... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: +28: +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 7: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 7: + 7: Loading extension module utils...Loading extension module utils... + 7: + 8: Loading extension module utils... + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... + 8: Loading extension module utils... + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 7: + 7: + 7: Loading extension module utils...Loading extension module utils... + 7: + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +30: +30: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +30: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +30: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +30: +30: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...No modifications detected for re-loaded extension module utils, skipping build step... +29: +29: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +31: +31: Loading extension module utils... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils...Loading extension module utils... +28: +28: +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: + 5: + 5: + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: + 5: + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 1: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... + 1: + 1: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 1: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 4: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 4: + 4: Loading extension module utils...Loading extension module utils... + 4: + 2: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 5: + 5: Loading extension module utils...Loading extension module utils... + 5: + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 6: + 6: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 3: + 3: Loading extension module utils...Loading extension module utils... + 3: + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils...Loading extension module utils... + 8: + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings + 0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") diff --git a/1b121b21b/logs/2088000.out b/1b121b21b/logs/2088000.out new file mode 100644 index 0000000000000000000000000000000000000000..81a99f7a4efb3f433faf5159f18b136c82815c34 --- /dev/null +++ b/1b121b21b/logs/2088000.out @@ -0,0 +1,10314 @@ +Model parameters: d_model 1792 ffw_size 7168 kv_size 128 n_heads 14 n_layers 26 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 26 --hidden-size 1792 --num-attention-heads 14 --kv-channels 128 --ffn-hidden-size 7168 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 1 --global-batch-size 256 --train-samples 10_156_250 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-1b121b --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 10_156_250 --lr-warmup-samples 101_563 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 10000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_1b121b --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_1b121b --load checkpoints_1b121b --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2088000.json --zero-stage 0 +START 2088000: Wed Nov 30 09:12:48 EET 2022 + 0: + 0: + 0: ======================= ROCm System Management Interface ======================= + 0: ================================= Concise Info ================================= + 0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 0: 0 48.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 2 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 4 48.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 6 46.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: ================================================================================ + 0: ============================= End of ROCm SMI Log ============================== +21: +21: +21: ======================= ROCm System Management Interface ======================= +21: ================================= Concise Info ================================= +21: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +21: 0 50.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 2 40.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 4 43.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 6 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: ================================================================================ +21: ============================= End of ROCm SMI Log ============================== +19: +19: +19: ======================= ROCm System Management Interface ======================= +19: ================================= Concise Info ================================= +19: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +19: 0 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 2 39.0c 99.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 4 47.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 6 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: ================================================================================ +19: ============================= End of ROCm SMI Log ============================== +29: +29: +29: ======================= ROCm System Management Interface ======================= +29: ================================= Concise Info ================================= +29: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +29: 0 48.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 2 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 4 46.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 6 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: ================================================================================ +29: ============================= End of ROCm SMI Log ============================== + 3: + 3: + 3: ======================= ROCm System Management Interface ======================= + 3: ================================= Concise Info ================================= + 3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 3: 0 46.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 2 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 4 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 6 39.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: ================================================================================ + 3: ============================= End of ROCm SMI Log ============================== +23: +23: +23: ======================= ROCm System Management Interface ======================= +23: ================================= Concise Info ================================= +23: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +23: 0 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 2 38.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 4 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 6 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: ================================================================================ +23: ============================= End of ROCm SMI Log ============================== +24: +24: +24: ======================= ROCm System Management Interface ======================= +24: ================================= Concise Info ================================= +24: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +24: 0 44.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 1 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 2 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 4 40.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 6 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: ================================================================================ +24: ============================= End of ROCm SMI Log ============================== +30: +30: +30: ======================= ROCm System Management Interface ======================= +30: ================================= Concise Info ================================= +30: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +30: 0 48.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 2 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 4 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 6 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: ================================================================================ +30: ============================= End of ROCm SMI Log ============================== + 5: + 5: + 5: ======================= ROCm System Management Interface ======================= + 5: ================================= Concise Info ================================= + 5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 5: 0 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 2 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 4 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 6 35.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: ================================================================================ + 5: ============================= End of ROCm SMI Log ============================== +13: +13: +13: ======================= ROCm System Management Interface ======================= +13: ================================= Concise Info ================================= +13: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +13: 0 43.0c 100.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 2 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 4 40.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 6 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: ================================================================================ +13: ============================= End of ROCm SMI Log ============================== + 6: + 6: + 6: ======================= ROCm System Management Interface ======================= + 6: ================================= Concise Info ================================= + 6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 6: 0 45.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 2 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 4 45.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 6 39.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: ================================================================================ + 6: ============================= End of ROCm SMI Log ============================== +12: +12: +12: ======================= ROCm System Management Interface ======================= +12: ================================= Concise Info ================================= +12: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +12: 0 47.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 2 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 4 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 6 38.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: ================================================================================ +12: ============================= End of ROCm SMI Log ============================== +27: +27: +27: ======================= ROCm System Management Interface ======================= +27: ================================= Concise Info ================================= +27: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +27: 0 37.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 1 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 2 42.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 4 40.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 6 43.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: ================================================================================ +27: ============================= End of ROCm SMI Log ============================== + 7: + 7: + 7: ======================= ROCm System Management Interface ======================= + 7: ================================= Concise Info ================================= + 7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 7: 0 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 2 39.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 4 49.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 6 44.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: ================================================================================ + 7: ============================= End of ROCm SMI Log ============================== + 8: + 8: + 8: ======================= ROCm System Management Interface ======================= + 8: ================================= Concise Info ================================= + 8: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 8: 0 47.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 2 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 3 38.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 4 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 6 42.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: ================================================================================ + 8: ============================= End of ROCm SMI Log ============================== + 9: + 9: + 9: ======================= ROCm System Management Interface ======================= + 9: ================================= Concise Info ================================= + 9: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 9: 0 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 2 40.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 4 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 6 42.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: ================================================================================ + 9: ============================= End of ROCm SMI Log ============================== +20: +20: +20: ======================= ROCm System Management Interface ======================= +20: ================================= Concise Info ================================= +20: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +20: 0 47.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 2 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 4 48.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 6 45.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: ================================================================================ +20: ============================= End of ROCm SMI Log ============================== +10: +10: +10: ======================= ROCm System Management Interface ======================= +10: ================================= Concise Info ================================= +10: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +10: 0 44.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 2 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 4 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 6 44.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: ================================================================================ +10: ============================= End of ROCm SMI Log ============================== +17: +17: +17: ======================= ROCm System Management Interface ======================= +17: ================================= Concise Info ================================= +17: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +17: 0 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 2 47.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 4 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 6 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: ================================================================================ +17: ============================= End of ROCm SMI Log ============================== +16: +16: +16: ======================= ROCm System Management Interface ======================= +16: ================================= Concise Info ================================= +16: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +16: 0 47.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 2 41.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 4 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 6 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: ================================================================================ +16: ============================= End of ROCm SMI Log ============================== +26: +26: +26: ======================= ROCm System Management Interface ======================= +26: ================================= Concise Info ================================= +26: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +26: 0 50.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 2 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 4 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 6 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: ================================================================================ +26: ============================= End of ROCm SMI Log ============================== +11: +11: +11: ======================= ROCm System Management Interface ======================= +11: ================================= Concise Info ================================= +11: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +11: 0 47.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 2 39.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 4 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 6 45.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: ================================================================================ +11: ============================= End of ROCm SMI Log ============================== +22: +22: +22: ======================= ROCm System Management Interface ======================= +22: ================================= Concise Info ================================= +22: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +22: 0 50.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 2 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 4 48.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 6 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: ================================================================================ +22: ============================= End of ROCm SMI Log ============================== + 2: + 2: + 2: ======================= ROCm System Management Interface ======================= + 2: ================================= Concise Info ================================= + 2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 2: 0 48.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 2 48.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 4 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 6 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: ================================================================================ + 2: ============================= End of ROCm SMI Log ============================== +31: +31: +31: ======================= ROCm System Management Interface ======================= +31: ================================= Concise Info ================================= +31: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +31: 0 45.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 2 38.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 4 48.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 6 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: ================================================================================ +31: ============================= End of ROCm SMI Log ============================== +18: +18: +18: ======================= ROCm System Management Interface ======================= +18: ================================= Concise Info ================================= +18: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +18: 0 51.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 2 41.0c 100.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 4 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 6 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: ================================================================================ +18: ============================= End of ROCm SMI Log ============================== + 1: + 1: + 1: ======================= ROCm System Management Interface ======================= + 1: ================================= Concise Info ================================= + 1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 1: 0 45.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 2 40.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 4 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 6 49.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: ================================================================================ + 1: ============================= End of ROCm SMI Log ============================== +15: +15: +15: ======================= ROCm System Management Interface ======================= +15: ================================= Concise Info ================================= +15: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +15: 0 46.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 2 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 4 47.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 6 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: ================================================================================ +15: ============================= End of ROCm SMI Log ============================== +14: +14: +14: ======================= ROCm System Management Interface ======================= +14: ================================= Concise Info ================================= +14: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +14: 0 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 2 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 4 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 6 39.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: ================================================================================ +14: ============================= End of ROCm SMI Log ============================== +28: +28: +28: ======================= ROCm System Management Interface ======================= +28: ================================= Concise Info ================================= +28: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +28: 0 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 2 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 4 46.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 6 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: ================================================================================ +28: ============================= End of ROCm SMI Log ============================== +25: +25: +25: ======================= ROCm System Management Interface ======================= +25: ================================= Concise Info ================================= +25: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +25: 0 43.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 2 40.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 4 42.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 6 46.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: ================================================================================ +25: ============================= End of ROCm SMI Log ============================== + 4: + 4: + 4: ======================= ROCm System Management Interface ======================= + 4: ================================= Concise Info ================================= + 4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 4: 0 47.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 2 49.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 4 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 6 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: ================================================================================ + 4: ============================= End of ROCm SMI Log ============================== +23: Launching on nid006148 (23/32), master nid006125 port 9999, GPUs 8, CUDA: True +19: Launching on nid006144 (19/32), master nid006125 port 9999, GPUs 8, CUDA: True + 7: Launching on nid006132 (7/32), master nid006125 port 9999, GPUs 8, CUDA: True +18: Launching on nid006143 (18/32), master nid006125 port 9999, GPUs 8, CUDA: True + 1: Launching on nid006126 (1/32), master nid006125 port 9999, GPUs 8, CUDA: True + 4: Launching on nid006129 (4/32), master nid006125 port 9999, GPUs 8, CUDA: True +25: Launching on nid006150 (25/32), master nid006125 port 9999, GPUs 8, CUDA: True +24: Launching on nid006149 (24/32), master nid006125 port 9999, GPUs 8, CUDA: True + 8: Launching on nid006133 (8/32), master nid006125 port 9999, GPUs 8, CUDA: True + 9: Launching on nid006134 (9/32), master nid006125 port 9999, GPUs 8, CUDA: True +26: Launching on nid006151 (26/32), master nid006125 port 9999, GPUs 8, CUDA: True +21: Launching on nid006146 (21/32), master nid006125 port 9999, GPUs 8, CUDA: True + 3: Launching on nid006128 (3/32), master nid006125 port 9999, GPUs 8, CUDA: True +15: Launching on nid006140 (15/32), master nid006125 port 9999, GPUs 8, CUDA: True +28: Launching on nid006153 (28/32), master nid006125 port 9999, GPUs 8, CUDA: True +10: Launching on nid006135 (10/32), master nid006125 port 9999, GPUs 8, CUDA: True +27: Launching on nid006152 (27/32), master nid006125 port 9999, GPUs 8, CUDA: True +12: Launching on nid006137 (12/32), master nid006125 port 9999, GPUs 8, CUDA: True +17: Launching on nid006142 (17/32), master nid006125 port 9999, GPUs 8, CUDA: True + 0: Launching on nid006125 (0/32), master nid006125 port 9999, GPUs 8, CUDA: True +16: Launching on nid006141 (16/32), master nid006125 port 9999, GPUs 8, CUDA: True +22: Launching on nid006147 (22/32), master nid006125 port 9999, GPUs 8, CUDA: True +20: Launching on nid006145 (20/32), master nid006125 port 9999, GPUs 8, CUDA: True +29: Launching on nid006154 (29/32), master nid006125 port 9999, GPUs 8, CUDA: True +14: Launching on nid006139 (14/32), master nid006125 port 9999, GPUs 8, CUDA: True +31: Launching on nid006156 (31/32), master nid006125 port 9999, GPUs 8, CUDA: True + 2: Launching on nid006127 (2/32), master nid006125 port 9999, GPUs 8, CUDA: True +13: Launching on nid006138 (13/32), master nid006125 port 9999, GPUs 8, CUDA: True +11: Launching on nid006136 (11/32), master nid006125 port 9999, GPUs 8, CUDA: True + 5: Launching on nid006130 (5/32), master nid006125 port 9999, GPUs 8, CUDA: True +30: Launching on nid006155 (30/32), master nid006125 port 9999, GPUs 8, CUDA: True + 6: Launching on nid006131 (6/32), master nid006125 port 9999, GPUs 8, CUDA: True + 0: using world size: 256, data-parallel-size: 256, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 + 0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. + 0: using torch.bfloat16 for parameters ... + 0: ------------------------ arguments ------------------------ + 0: abort_on_unmet_fused_kernel_constraints ......... False + 0: accumulate_allreduce_grads_in_fp32 .............. True + 0: adam_beta1 ...................................... 0.9 + 0: adam_beta2 ...................................... 0.999 + 0: adam_eps ........................................ 1e-08 + 0: adlr_autoresume ................................. False + 0: adlr_autoresume_interval ........................ 1000 + 0: apply_query_key_layer_scaling ................... True + 0: apply_residual_connection_post_layernorm ........ False + 0: attention_dropout ............................... 0.1 + 0: attention_softmax_in_fp32 ....................... False + 0: bert_binary_head ................................ True + 0: bert_load ....................................... None + 0: bf16 ............................................ True + 0: bias_dropout_fusion ............................. True + 0: bias_gelu_fusion ................................ True + 0: biencoder_projection_dim ........................ 0 + 0: biencoder_shared_query_context_model ............ False + 0: block_data_path ................................. None + 0: checkpoint_activations .......................... False + 0: checkpoint_in_cpu ............................... False + 0: checkpoint_num_layers ........................... 1 + 0: clip_grad ....................................... 1.0 + 0: codecarbon_dir .................................. None + 0: consumed_train_samples .......................... 0 + 0: consumed_train_tokens ........................... 0 + 0: consumed_valid_samples .......................... 0 + 0: contigious_checkpointing ........................ False + 0: cpu_optimizer ................................... False + 0: cpu_torch_adam .................................. False + 0: curriculum_learning ............................. False + 0: data_impl ....................................... mmap + 0: data_parallel_size .............................. 256 + 0: data_path ....................................... ['/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document'] + 0: dataloader_type ................................. single + 0: DDP_impl ........................................ local + 0: decoder_seq_length .............................. None + 0: deepscale ....................................... False + 0: deepscale_config ................................ None + 0: deepspeed ....................................... True + 0: deepspeed_activation_checkpointing .............. False + 0: deepspeed_config ................................ ds_configs/2088000.json + 0: deepspeed_mpi ................................... False + 0: distribute_checkpointed_activations ............. False + 0: distributed_backend ............................. nccl + 0: embed_layernorm ................................. False + 0: embedding_path .................................. None + 0: encoder_seq_length .............................. 2048 + 0: eod_mask_loss ................................... False + 0: eval_interval ................................... 1000 + 0: eval_iters ...................................... 1 + 0: eval_only ....................................... None + 0: evidence_data_path .............................. None + 0: exit_duration_in_mins ........................... None + 0: exit_interval ................................... None + 0: ffn_hidden_size ................................. 7168 + 0: finetune ........................................ False + 0: fp16 ............................................ False + 0: fp16_lm_cross_entropy ........................... False + 0: fp32_residual_connection ........................ False + 0: gigaflos_no_embeds .............................. 0 + 0: global_batch_size ............................... 256 + 0: glu_activation .................................. None + 0: hidden_dropout .................................. 0.1 + 0: hidden_size ..................................... 1792 + 0: hysteresis ...................................... 2 + 0: ict_head_size ................................... None + 0: ict_load ........................................ None + 0: img_dim ......................................... 224 + 0: indexer_batch_size .............................. 128 + 0: indexer_log_interval ............................ 1000 + 0: inference ....................................... False + 0: init_method_std ................................. 0.02 + 0: init_method_xavier_uniform ...................... False + 0: initial_loss_scale .............................. 4294967296 + 0: kill_switch_path ................................ kill-switch-1b121b + 0: kv_channels ..................................... 128 + 0: layer_norm_fusion ............................... True + 0: layernorm_epsilon ............................... 1e-05 + 0: lazy_mpu_init ................................... None + 0: load ............................................ checkpoints_1b121b + 0: local_rank ...................................... None + 0: log_batch_size_to_tensorboard ................... True + 0: log_interval .................................... 10 + 0: log_learning_rate_to_tensorboard ................ True + 0: log_level ....................................... None + 0: log_level_replica ............................... None + 0: log_loss_scale_to_tensorboard ................... True + 0: log_num_zeros_in_grad ........................... False + 0: log_params_norm ................................. False + 0: log_path ........................................ None + 0: log_timers_to_tensorboard ....................... True + 0: log_validation_ppl_to_tensorboard ............... True + 0: loss_on_targets_only ............................ False + 0: loss_scale ...................................... None + 0: loss_scale_window ............................... 1000 + 0: lr .............................................. 0.0002 + 0: lr_decay_iters .................................. None + 0: lr_decay_samples ................................ 10156250 + 0: lr_decay_style .................................. cosine + 0: lr_decay_tokens ................................. None + 0: lr_warmup_fraction .............................. None + 0: lr_warmup_iters ................................. 0 + 0: lr_warmup_samples ............................... 101563 + 0: make_vocab_size_divisible_by .................... 128 + 0: mask_prob ....................................... 0.15 + 0: masked_softmax_fusion ........................... True + 0: max_position_embeddings ......................... 2048 + 0: mean_noise_span_length .......................... None + 0: memory_centric_tiled_linear ..................... False + 0: merge_file ...................................... gpt2/merges.txt + 0: micro_batch_size ................................ 1 + 0: min_loss_scale .................................. 1.0 + 0: min_lr .......................................... 2e-05 + 0: mmap_warmup ..................................... False + 0: no_load_optim ................................... None + 0: no_load_rng ..................................... None + 0: no_save_optim ................................... None + 0: no_save_rng ..................................... None + 0: noise_density ................................... None + 0: num_attention_heads ............................. 14 + 0: num_channels .................................... 3 + 0: num_classes ..................................... 1000 + 0: num_layers ...................................... 26 + 0: num_layers_per_virtual_pipeline_stage ........... None + 0: num_workers ..................................... 2 + 0: onnx_safe ....................................... None + 0: openai_gelu ..................................... False + 0: optimizer ....................................... adam + 0: optimizer_fusion ................................ True + 0: override_lr_scheduler ........................... False + 0: pad_vocab_size_to ............................... None + 0: params_dtype .................................... torch.bfloat16 + 0: partition_activations ........................... False + 0: patch_dim ....................................... 16 + 0: pipeline_model_parallel_size .................... 1 + 0: position_embedding_type ......................... PositionEmbeddingType.absolute + 0: pp_partition_method ............................. None + 0: profile_backward ................................ False + 0: query_in_block_prob ............................. 0.1 + 0: rampup_batch_size ............................... None + 0: rank ............................................ 0 + 0: remote_device ................................... none + 0: reset_attention_mask ............................ False + 0: reset_position_ids .............................. False + 0: retriever_report_topk_accuracies ................ [] + 0: retriever_score_scaling ......................... False + 0: retriever_seq_length ............................ 256 + 0: reweight_loss_based_on_position_frequency ....... False + 0: sample_rate ..................................... 1.0 + 0: save ............................................ checkpoints_1b121b + 0: save_interval ................................... 10000 + 0: scatter_gather_tensors_in_pipeline .............. True + 0: scattered_embeddings ............................ False + 0: seed ............................................ 1234 + 0: seq_length ...................................... 2048 + 0: sgd_momentum .................................... 0.9 + 0: short_seq_prob .................................. 0.1 + 0: skip_train_iteration_range ...................... None + 0: split ........................................... 949,50,1 + 0: split_transformers .............................. False + 0: sync_tp_duplicated_parameters ................... False + 0: synchronize_each_layer .......................... False + 0: tensor_model_parallel_size ...................... 1 + 0: tensorboard_dir ................................. tensorboard_1b121b + 0: tensorboard_log_interval ........................ 1 + 0: tensorboard_queue_size .......................... 5 + 0: test_weighted_split_names ....................... None + 0: test_weighted_split_paths ....................... None + 0: test_weighted_split_paths_path .................. None + 0: test_weighted_split_splits ...................... None + 0: test_weighted_split_weights ..................... None + 0: tile_factor ..................................... 1 + 0: titles_data_path ................................ None + 0: tokenizer_name_or_path .......................... None + 0: tokenizer_type .................................. GPT2BPETokenizer + 0: train_iters ..................................... None + 0: train_samples ................................... 10156250 + 0: train_tokens .................................... None + 0: train_weighted_split_paths ...................... None + 0: train_weighted_split_paths_path ................. None + 0: universal_checkpoint ............................ False + 0: use_bnb_optimizer ............................... False + 0: use_checkpoint_lr_scheduler ..................... False + 0: use_contiguous_buffers_in_ddp ................... True + 0: use_cpu_initialization .......................... None + 0: use_one_sent_docs ............................... False + 0: use_pin_memory .................................. False + 0: valid_num_workers ............................... 2 + 0: valid_weighted_split_names ...................... None + 0: valid_weighted_split_paths ...................... None + 0: valid_weighted_split_paths_path ................. None + 0: valid_weighted_split_splits ..................... None + 0: valid_weighted_split_weights .................... None + 0: virtual_pipeline_model_parallel_size ............ None + 0: vocab_extra_ids ................................. 0 + 0: vocab_file ...................................... gpt2/vocab.json + 0: weight_decay .................................... 0.1 + 0: world_size ...................................... 256 + 0: zero_allgather_bucket_size ...................... 0.0 + 0: zero_contigious_gradients ....................... False + 0: zero_reduce_bucket_size ......................... 0.0 + 0: zero_reduce_scatter ............................. False + 0: zero_stage ...................................... 0 + 0: -------------------- end of arguments --------------------- + 0: setting number of micro-batches to constant 1 + 0: > building GPT2BPETokenizer tokenizer ... + 0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) + 0: DeepSpeed general environment info: + 0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] + 0: torch version .................... 1.13.0+rocm5.2 + 0: torch cuda version ............... None + 0: torch hip version ................ 5.2.21151-afdc89f8 + 0: nvcc version ..................... None + 0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] + 0: deepspeed info ................... 0.7.5, unknown, unknown + 0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 + 0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** + 0: > initializing torch distributed ... + 0: [2022-11-30 09:13:45,678] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +31: > setting tensorboard ... + 0: > initializing tensor model parallel with size 1 + 0: > initializing pipeline model parallel with size 1 + 0: > setting random seeds to 1234 ... + 0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 + 0: > compiling dataset index builder ... + 0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' + 0: make: Nothing to be done for 'default'. + 0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' + 0: >>> done with dataset index builder. Compilation time: 0.097 seconds + 0: WARNING: constraints for invoking optimized fused softmax kernel are not met. We default back to unfused kernel invocations. + 0: > compiling and loading fused kernels ... + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 87 + 0: ninja: no work to do. + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 63 + 0: [1/1] c++ scaled_masked_softmax_hip.o scaled_masked_softmax_hip.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_masked_softmax_cuda.so + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 67 + 0: [1/1] c++ layer_norm_cuda.o layer_norm_hip_kernel.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o fused_mix_prec_layer_norm_cuda.so + 0: >>> done with compiling and loading fused kernels. Compilation time: 23.198 seconds + 0: time to initialize megatron (seconds): 77.830 + 0: [after megatron is initialized] datetime: 2022-11-30 09:14:21 + 0: building GPT model ... + 0: [2022-11-30 09:14:21,888] [INFO] [utils.py:827:see_memory_usage] Before Building Model + 0: [2022-11-30 09:14:21,889] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB + 0: [2022-11-30 09:14:21,889] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 39.19 GB, percent = 7.8% + 0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None + 0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi + 0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 + 0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63, ProcessCoord(pipe=0, data=64, model=0): 64, ProcessCoord(pipe=0, data=65, model=0): 65, ProcessCoord(pipe=0, data=66, model=0): 66, ProcessCoord(pipe=0, data=67, model=0): 67, ProcessCoord(pipe=0, data=68, model=0): 68, ProcessCoord(pipe=0, data=69, model=0): + 0: 69, ProcessCoord(pipe=0, data=70, model=0): 70, ProcessCoord(pipe=0, data=71, model=0): 71, ProcessCoord(pipe=0, data=72, model=0): 72, ProcessCoord(pipe=0, data=73, model=0): 73, ProcessCoord(pipe=0, data=74, model=0): 74, ProcessCoord(pipe=0, data=75, model=0): 75, ProcessCoord(pipe=0, data=76, model=0): 76, ProcessCoord(pipe=0, data=77, model=0): 77, ProcessCoord(pipe=0, data=78, model=0): 78, ProcessCoord(pipe=0, data=79, model=0): 79, ProcessCoord(pipe=0, data=80, model=0): 80, ProcessCoord(pipe=0, data=81, model=0): 81, ProcessCoord(pipe=0, data=82, model=0): 82, ProcessCoord(pipe=0, data=83, model=0): 83, ProcessCoord(pipe=0, data=84, model=0): 84, ProcessCoord(pipe=0, data=85, model=0): 85, ProcessCoord(pipe=0, data=86, model=0): 86, ProcessCoord(pipe=0, data=87, model=0): 87, ProcessCoord(pipe=0, data=88, model=0): 88, ProcessCoord(pipe=0, data=89, model=0): 89, ProcessCoord(pipe=0, data=90, model=0): 90, ProcessCoord(pipe=0, data=91, model=0): 91, ProcessCoord(pipe=0, data=92, model=0): 92, Process + 0: Coord(pipe=0, data=93, model=0): 93, ProcessCoord(pipe=0, data=94, model=0): 94, ProcessCoord(pipe=0, data=95, model=0): 95, ProcessCoord(pipe=0, data=96, model=0): 96, ProcessCoord(pipe=0, data=97, model=0): 97, ProcessCoord(pipe=0, data=98, model=0): 98, ProcessCoord(pipe=0, data=99, model=0): 99, ProcessCoord(pipe=0, data=100, model=0): 100, ProcessCoord(pipe=0, data=101, model=0): 101, ProcessCoord(pipe=0, data=102, model=0): 102, ProcessCoord(pipe=0, data=103, model=0): 103, ProcessCoord(pipe=0, data=104, model=0): 104, ProcessCoord(pipe=0, data=105, model=0): 105, ProcessCoord(pipe=0, data=106, model=0): 106, ProcessCoord(pipe=0, data=107, model=0): 107, ProcessCoord(pipe=0, data=108, model=0): 108, ProcessCoord(pipe=0, data=109, model=0): 109, ProcessCoord(pipe=0, data=110, model=0): 110, ProcessCoord(pipe=0, data=111, model=0): 111, ProcessCoord(pipe=0, data=112, model=0): 112, ProcessCoord(pipe=0, data=113, model=0): 113, ProcessCoord(pipe=0, data=114, model=0): 114, ProcessCoord(pipe=0, data=115, mo + 0: del=0): 115, ProcessCoord(pipe=0, data=116, model=0): 116, ProcessCoord(pipe=0, data=117, model=0): 117, ProcessCoord(pipe=0, data=118, model=0): 118, ProcessCoord(pipe=0, data=119, model=0): 119, ProcessCoord(pipe=0, data=120, model=0): 120, ProcessCoord(pipe=0, data=121, model=0): 121, ProcessCoord(pipe=0, data=122, model=0): 122, ProcessCoord(pipe=0, data=123, model=0): 123, ProcessCoord(pipe=0, data=124, model=0): 124, ProcessCoord(pipe=0, data=125, model=0): 125, ProcessCoord(pipe=0, data=126, model=0): 126, ProcessCoord(pipe=0, data=127, model=0): 127, ProcessCoord(pipe=0, data=128, model=0): 128, ProcessCoord(pipe=0, data=129, model=0): 129, ProcessCoord(pipe=0, data=130, model=0): 130, ProcessCoord(pipe=0, data=131, model=0): 131, ProcessCoord(pipe=0, data=132, model=0): 132, ProcessCoord(pipe=0, data=133, model=0): 133, ProcessCoord(pipe=0, data=134, model=0): 134, ProcessCoord(pipe=0, data=135, model=0): 135, ProcessCoord(pipe=0, data=136, model=0): 136, ProcessCoord(pipe=0, data=137, model=0): 137, + 0: ProcessCoord(pipe=0, data=138, model=0): 138, ProcessCoord(pipe=0, data=139, model=0): 139, ProcessCoord(pipe=0, data=140, model=0): 140, ProcessCoord(pipe=0, data=141, model=0): 141, ProcessCoord(pipe=0, data=142, model=0): 142, ProcessCoord(pipe=0, data=143, model=0): 143, ProcessCoord(pipe=0, data=144, model=0): 144, ProcessCoord(pipe=0, data=145, model=0): 145, ProcessCoord(pipe=0, data=146, model=0): 146, ProcessCoord(pipe=0, data=147, model=0): 147, ProcessCoord(pipe=0, data=148, model=0): 148, ProcessCoord(pipe=0, data=149, model=0): 149, ProcessCoord(pipe=0, data=150, model=0): 150, ProcessCoord(pipe=0, data=151, model=0): 151, ProcessCoord(pipe=0, data=152, model=0): 152, ProcessCoord(pipe=0, data=153, model=0): 153, ProcessCoord(pipe=0, data=154, model=0): 154, ProcessCoord(pipe=0, data=155, model=0): 155, ProcessCoord(pipe=0, data=156, model=0): 156, ProcessCoord(pipe=0, data=157, model=0): 157, ProcessCoord(pipe=0, data=158, model=0): 158, ProcessCoord(pipe=0, data=159, model=0): 159, ProcessCoor + 0: d(pipe=0, data=160, model=0): 160, ProcessCoord(pipe=0, data=161, model=0): 161, ProcessCoord(pipe=0, data=162, model=0): 162, ProcessCoord(pipe=0, data=163, model=0): 163, ProcessCoord(pipe=0, data=164, model=0): 164, ProcessCoord(pipe=0, data=165, model=0): 165, ProcessCoord(pipe=0, data=166, model=0): 166, ProcessCoord(pipe=0, data=167, model=0): 167, ProcessCoord(pipe=0, data=168, model=0): 168, ProcessCoord(pipe=0, data=169, model=0): 169, ProcessCoord(pipe=0, data=170, model=0): 170, ProcessCoord(pipe=0, data=171, model=0): 171, ProcessCoord(pipe=0, data=172, model=0): 172, ProcessCoord(pipe=0, data=173, model=0): 173, ProcessCoord(pipe=0, data=174, model=0): 174, ProcessCoord(pipe=0, data=175, model=0): 175, ProcessCoord(pipe=0, data=176, model=0): 176, ProcessCoord(pipe=0, data=177, model=0): 177, ProcessCoord(pipe=0, data=178, model=0): 178, ProcessCoord(pipe=0, data=179, model=0): 179, ProcessCoord(pipe=0, data=180, model=0): 180, ProcessCoord(pipe=0, data=181, model=0): 181, ProcessCoord(pipe=0, da + 0: ta=182, model=0): 182, ProcessCoord(pipe=0, data=183, model=0): 183, ProcessCoord(pipe=0, data=184, model=0): 184, ProcessCoord(pipe=0, data=185, model=0): 185, ProcessCoord(pipe=0, data=186, model=0): 186, ProcessCoord(pipe=0, data=187, model=0): 187, ProcessCoord(pipe=0, data=188, model=0): 188, ProcessCoord(pipe=0, data=189, model=0): 189, ProcessCoord(pipe=0, data=190, model=0): 190, ProcessCoord(pipe=0, data=191, model=0): 191, ProcessCoord(pipe=0, data=192, model=0): 192, ProcessCoord(pipe=0, data=193, model=0): 193, ProcessCoord(pipe=0, data=194, model=0): 194, ProcessCoord(pipe=0, data=195, model=0): 195, ProcessCoord(pipe=0, data=196, model=0): 196, ProcessCoord(pipe=0, data=197, model=0): 197, ProcessCoord(pipe=0, data=198, model=0): 198, ProcessCoord(pipe=0, data=199, model=0): 199, ProcessCoord(pipe=0, data=200, model=0): 200, ProcessCoord(pipe=0, data=201, model=0): 201, ProcessCoord(pipe=0, data=202, model=0): 202, ProcessCoord(pipe=0, data=203, model=0): 203, ProcessCoord(pipe=0, data=204, mode + 0: l=0): 204, ProcessCoord(pipe=0, data=205, model=0): 205, ProcessCoord(pipe=0, data=206, model=0): 206, ProcessCoord(pipe=0, data=207, model=0): 207, ProcessCoord(pipe=0, data=208, model=0): 208, ProcessCoord(pipe=0, data=209, model=0): 209, ProcessCoord(pipe=0, data=210, model=0): 210, ProcessCoord(pipe=0, data=211, model=0): 211, ProcessCoord(pipe=0, data=212, model=0): 212, ProcessCoord(pipe=0, data=213, model=0): 213, ProcessCoord(pipe=0, data=214, model=0): 214, ProcessCoord(pipe=0, data=215, model=0): 215, ProcessCoord(pipe=0, data=216, model=0): 216, ProcessCoord(pipe=0, data=217, model=0): 217, ProcessCoord(pipe=0, data=218, model=0): 218, ProcessCoord(pipe=0, data=219, model=0): 219, ProcessCoord(pipe=0, data=220, model=0): 220, ProcessCoord(pipe=0, data=221, model=0): 221, ProcessCoord(pipe=0, data=222, model=0): 222, ProcessCoord(pipe=0, data=223, model=0): 223, ProcessCoord(pipe=0, data=224, model=0): 224, ProcessCoord(pipe=0, data=225, model=0): 225, ProcessCoord(pipe=0, data=226, model=0): 226, P + 0: rocessCoord(pipe=0, data=227, model=0): 227, ProcessCoord(pipe=0, data=228, model=0): 228, ProcessCoord(pipe=0, data=229, model=0): 229, ProcessCoord(pipe=0, data=230, model=0): 230, ProcessCoord(pipe=0, data=231, model=0): 231, ProcessCoord(pipe=0, data=232, model=0): 232, ProcessCoord(pipe=0, data=233, model=0): 233, ProcessCoord(pipe=0, data=234, model=0): 234, ProcessCoord(pipe=0, data=235, model=0): 235, ProcessCoord(pipe=0, data=236, model=0): 236, ProcessCoord(pipe=0, data=237, model=0): 237, ProcessCoord(pipe=0, data=238, model=0): 238, ProcessCoord(pipe=0, data=239, model=0): 239, ProcessCoord(pipe=0, data=240, model=0): 240, ProcessCoord(pipe=0, data=241, model=0): 241, ProcessCoord(pipe=0, data=242, model=0): 242, ProcessCoord(pipe=0, data=243, model=0): 243, ProcessCoord(pipe=0, data=244, model=0): 244, ProcessCoord(pipe=0, data=245, model=0): 245, ProcessCoord(pipe=0, data=246, model=0): 246, ProcessCoord(pipe=0, data=247, model=0): 247, ProcessCoord(pipe=0, data=248, model=0): 248, ProcessCoord( + 0: pipe=0, data=249, model=0): 249, ProcessCoord(pipe=0, data=250, model=0): 250, ProcessCoord(pipe=0, data=251, model=0): 251, ProcessCoord(pipe=0, data=252, model=0): 252, ProcessCoord(pipe=0, data=253, model=0): 253, ProcessCoord(pipe=0, data=254, model=0): 254, ProcessCoord(pipe=0, data=255, model=0): 255} + 0: [2022-11-30 09:14:30,946] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer + 0: stage=0 layers=33 + 0: 0: _to_float16 + 0: 1: EmbeddingPipe + 0: 2: + 0: 3: ParallelTransformerLayerPipe + 0: 4: ParallelTransformerLayerPipe + 0: 5: ParallelTransformerLayerPipe + 0: 6: ParallelTransformerLayerPipe + 0: 7: ParallelTransformerLayerPipe + 0: 8: ParallelTransformerLayerPipe + 0: 9: ParallelTransformerLayerPipe + 0: 10: ParallelTransformerLayerPipe + 0: 11: ParallelTransformerLayerPipe + 0: 12: ParallelTransformerLayerPipe + 0: 13: ParallelTransformerLayerPipe + 0: 14: ParallelTransformerLayerPipe + 0: 15: ParallelTransformerLayerPipe + 0: 16: ParallelTransformerLayerPipe + 0: 17: ParallelTransformerLayerPipe + 0: 18: ParallelTransformerLayerPipe + 0: 19: ParallelTransformerLayerPipe + 0: 20: ParallelTransformerLayerPipe + 0: 21: ParallelTransformerLayerPipe + 0: 22: ParallelTransformerLayerPipe + 0: 23: ParallelTransformerLayerPipe + 0: 24: ParallelTransformerLayerPipe + 0: 25: ParallelTransformerLayerPipe + 0: 26: ParallelTransformerLayerPipe + 0: 27: ParallelTransformerLayerPipe + 0: 28: ParallelTransformerLayerPipe + 0: 29: undo + 0: 30: MixedFusedLayerNorm + 0: 31: EmbeddingPipe + 0: 32: float16_to_fp32 + 0: loss: CrossEntropy + 0: [2022-11-30 09:14:31,143] [INFO] [utils.py:827:see_memory_usage] After Building Model + 0: [2022-11-30 09:14:31,144] [INFO] [utils.py:828:see_memory_usage] MA 2.05 GB Max_MA 2.05 GB CA 2.19 GB Max_CA 2 GB + 0: [2022-11-30 09:14:31,144] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 39.25 GB, percent = 7.8% + 0: setting training iterations to 39672 + 0: > learning rate decay style: cosine + 0: DeepSpeed is enabled. + 0: [2022-11-30 09:14:31,146] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown + 0: [2022-11-30 09:14:53,362] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False + 0: [2022-11-30 09:14:53,363] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer + 0: [2022-11-30 09:14:53,363] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer + 0: [2022-11-30 09:14:53,375] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam + 0: [2022-11-30 09:14:53,375] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer + 0: [2022-11-30 09:14:53,416] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer + 0: [2022-11-30 09:14:53,417] [INFO] [utils.py:828:see_memory_usage] MA 2.04 GB Max_MA 2.06 GB CA 2.19 GB Max_CA 2 GB + 0: [2022-11-30 09:14:53,417] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 39.95 GB, percent = 7.9% + 0: ninja: no work to do. + 0: Time to load utils op: 0.13459038734436035 seconds +24: Time to load utils op: 0.10811161994934082 seconds +29: Time to load utils op: 0.10802078247070312 seconds +28: Time to load utils op: 0.10855293273925781 seconds + 0: [2022-11-30 09:14:53,601] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 + 0: [2022-11-30 09:14:53,601] [INFO] [utils.py:828:see_memory_usage] MA 2.04 GB Max_MA 2.04 GB CA 2.19 GB Max_CA 2 GB + 0: [2022-11-30 09:14:53,601] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 39.95 GB, percent = 7.9% + 0: ninja: no work to do. + 0: [2022-11-30 09:14:53,672] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 + 0: [2022-11-30 09:14:53,673] [INFO] [utils.py:828:see_memory_usage] MA 4.22 GB Max_MA 4.22 GB CA 5.44 GB Max_CA 5 GB + 0: [2022-11-30 09:14:53,673] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 39.96 GB, percent = 7.9% + 0: Time to load utils op: 0.11915969848632812 seconds + 9: Time to load utils op: 0.11146354675292969 secondsTime to load utils op: 0.1114645004272461 seconds + 9: + 9: Time to load utils op: 0.11147141456604004 seconds + 9: Time to load utils op: 0.11150574684143066 seconds + 9: Time to load utils op: 0.1115102767944336 seconds + 9: Time to load utils op: 0.11150670051574707 secondsTime to load utils op: 0.11151123046875 seconds + 9: + 9: Time to load utils op: 0.1115262508392334 seconds +12: Time to load utils op: 0.11118769645690918 seconds +12: Time to load utils op: 0.11114811897277832 seconds +12: Time to load utils op: 0.11117100715637207 seconds +12: Time to load utils op: 0.11120414733886719 secondsTime to load utils op: 0.11117863655090332 seconds +12: +12: Time to load utils op: 0.11118602752685547 seconds +12: Time to load utils op: 0.11120867729187012 seconds +12: Time to load utils op: 0.11119723320007324 seconds +13: Time to load utils op: 0.1104426383972168 seconds +13: Time to load utils op: 0.11061692237854004 seconds +13: Time to load utils op: 0.11046075820922852 seconds +13: Time to load utils op: 0.11010408401489258 seconds +13: Time to load utils op: 0.11037635803222656 seconds +13: Time to load utils op: 0.11050939559936523 seconds +13: Time to load utils op: 0.1105501651763916 seconds +10: Time to load utils op: 0.11144685745239258 secondsTime to load utils op: 0.11144804954528809 seconds +10: +10: Time to load utils op: 0.11144685745239258 secondsTime to load utils op: 0.11145210266113281 seconds +10: +10: Time to load utils op: 0.11146235466003418 seconds +10: Time to load utils op: 0.11146402359008789 secondsTime to load utils op: 0.11145782470703125 seconds +10: +10: Time to load utils op: 0.11148571968078613 seconds +16: Time to load utils op: 0.10918092727661133 secondsTime to load utils op: 0.10959553718566895 seconds +16: +16: Time to load utils op: 0.10976982116699219 secondsTime to load utils op: 0.11031198501586914 seconds +16: +16: Time to load utils op: 0.11013436317443848 seconds +16: Time to load utils op: 0.11004233360290527 seconds +16: Time to load utils op: 0.10901618003845215 seconds +16: Time to load utils op: 0.10976839065551758 seconds + 7: Time to load utils op: 0.11310362815856934 seconds + 7: Time to load utils op: 0.1131277084350586 seconds + 7: Time to load utils op: 0.11313867568969727 seconds + 7: Time to load utils op: 0.1131601333618164 secondsTime to load utils op: 0.11316490173339844 seconds + 7: + 7: Time to load utils op: 0.11317586898803711 seconds + 7: Time to load utils op: 0.11318230628967285 seconds + 7: Time to load utils op: 0.11318564414978027 seconds +18: Time to load utils op: 0.10903286933898926 seconds +18: Time to load utils op: 0.10867881774902344 seconds +18: Time to load utils op: 0.11029458045959473 seconds +18: Time to load utils op: 0.1094655990600586 seconds +18: Time to load utils op: 0.10948729515075684 secondsTime to load utils op: 0.10989069938659668 secondsTime to load utils op: 0.10989069938659668 seconds +18: +18: +18: Time to load utils op: 0.11059069633483887 seconds +14: Time to load utils op: 0.11174345016479492 seconds +14: Time to load utils op: 0.11175298690795898 seconds +14: Time to load utils op: 0.11177277565002441 seconds +14: Time to load utils op: 0.11164975166320801 seconds +14: Time to load utils op: 0.11180758476257324 secondsTime to load utils op: 0.1118001937866211 secondsTime to load utils op: 0.11179971694946289 seconds +14: +14: +14: Time to load utils op: 0.1118156909942627 seconds +24: Time to load utils op: 0.10365986824035645 seconds +24: Time to load utils op: 0.10383892059326172 seconds +17: Time to load utils op: 0.10924434661865234 seconds +17: Time to load utils op: 0.10924053192138672 seconds +17: Time to load utils op: 0.10924720764160156 seconds +17: Time to load utils op: 0.10924816131591797 seconds +17: Time to load utils op: 0.10925507545471191 secondsTime to load utils op: 0.10925793647766113 secondsTime to load utils op: 0.10926365852355957 seconds +17: +17: +17: Time to load utils op: 0.10926604270935059 seconds +24: Time to load utils op: 0.10357022285461426 seconds +24: Time to load utils op: 0.10360050201416016 seconds +24: Time to load utils op: 0.10435247421264648 secondsTime to load utils op: 0.10436606407165527 seconds +24: +24: Time to load utils op: 0.10426163673400879 seconds +15: Time to load utils op: 0.11172771453857422 secondsTime to load utils op: 0.11173391342163086 seconds +15: +15: Time to load utils op: 0.11173653602600098 seconds +15: Time to load utils op: 0.11176776885986328 seconds +15: Time to load utils op: 0.11176896095275879 seconds +15: Time to load utils op: 0.11177778244018555 seconds +15: Time to load utils op: 0.11178421974182129 secondsTime to load utils op: 0.1117851734161377 seconds +15: +28: Time to load utils op: 0.10274243354797363 secondsTime to load utils op: 0.10295844078063965 seconds +28: +19: Time to load utils op: 0.11050915718078613 seconds +19: Time to load utils op: 0.11056137084960938 secondsTime to load utils op: 0.11056828498840332 seconds +19: +19: Time to load utils op: 0.1105804443359375 seconds +19: Time to load utils op: 0.11059069633483887 seconds +19: Time to load utils op: 0.11060523986816406 seconds +19: Time to load utils op: 0.11060690879821777 secondsTime to load utils op: 0.11061310768127441 seconds +19: +28: Time to load utils op: 0.1029202938079834 seconds +28: Time to load utils op: 0.10301327705383301 seconds +28: Time to load utils op: 0.10288691520690918 seconds +29: Time to load utils op: 0.10186481475830078 seconds +29: Time to load utils op: 0.10265827178955078 seconds +28: Time to load utils op: 0.10337972640991211 seconds +28: Time to load utils op: 0.10358071327209473 seconds +29: Time to load utils op: 0.10235357284545898 seconds +29: Time to load utils op: 0.10234236717224121 seconds +29: Time to load utils op: 0.10235953330993652 seconds +29: Time to load utils op: 0.10294795036315918 seconds +29: Time to load utils op: 0.10253667831420898 seconds +22: Time to load utils op: 0.11149072647094727 seconds +22: Time to load utils op: 0.11180663108825684 seconds +22: Time to load utils op: 0.11262702941894531 seconds +22: Time to load utils op: 0.11148452758789062 seconds +22: Time to load utils op: 0.11217498779296875 seconds +22: Time to load utils op: 0.11240720748901367 seconds +22: Time to load utils op: 0.1118769645690918 seconds +22: Time to load utils op: 0.11210775375366211 seconds +23: Time to load utils op: 0.11155009269714355 seconds +23: Time to load utils op: 0.11163473129272461 seconds +23: Time to load utils op: 0.11085987091064453 seconds +23: Time to load utils op: 0.11140847206115723 secondsTime to load utils op: 0.11212444305419922 seconds +23: +23: Time to load utils op: 0.11152005195617676 secondsTime to load utils op: 0.11117863655090332 seconds +23: +23: Time to load utils op: 0.11254191398620605 seconds +20: Time to load utils op: 0.11142945289611816 seconds +21: Time to load utils op: 0.11019754409790039 seconds +20: Time to load utils op: 0.11146879196166992 seconds +20: Time to load utils op: 0.11148333549499512 seconds +20: Time to load utils op: 0.11150360107421875 secondsTime to load utils op: 0.11150741577148438 seconds +20: +21: Time to load utils op: 0.1102132797241211 secondsTime to load utils op: 0.11022210121154785 seconds +21: +20: Time to load utils op: 0.11151957511901855 seconds +20: Time to load utils op: 0.1115262508392334 seconds +21: Time to load utils op: 0.11023473739624023 seconds +21: Time to load utils op: 0.11024641990661621 seconds +20: Time to load utils op: 0.11152315139770508 seconds +21: Time to load utils op: 0.1102604866027832 secondsTime to load utils op: 0.11024808883666992 seconds +21: +21: Time to load utils op: 0.11026787757873535 seconds +25: Time to load utils op: 0.11210823059082031 seconds +25: Time to load utils op: 0.11162066459655762 seconds +25: Time to load utils op: 0.11167144775390625 seconds +25: Time to load utils op: 0.11210441589355469 seconds +25: Time to load utils op: 0.11168813705444336 seconds +25: Time to load utils op: 0.11178040504455566 secondsTime to load utils op: 0.11212396621704102 seconds +25: +25: Time to load utils op: 0.11202478408813477 seconds +26: Time to load utils op: 0.11027693748474121 seconds +26: Time to load utils op: 0.11029314994812012 seconds +26: Time to load utils op: 0.1103060245513916 seconds +26: Time to load utils op: 0.11032366752624512 seconds +26: Time to load utils op: 0.1103215217590332 secondsTime to load utils op: 0.1103219985961914 seconds +26: +26: Time to load utils op: 0.11033344268798828 seconds +26: Time to load utils op: 0.1103353500366211 seconds + 0: [2022-11-30 09:14:53,706] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +27: Time to load utils op: 0.10991144180297852 seconds +27: Time to load utils op: 0.10994315147399902 seconds +27: Time to load utils op: 0.10995101928710938 seconds +27: Time to load utils op: 0.10998749732971191 secondsTime to load utils op: 0.10999035835266113 seconds +27: +27: Time to load utils op: 0.1100010871887207 seconds +27: Time to load utils op: 0.10999584197998047 secondsTime to load utils op: 0.11001348495483398 seconds +27: + 0: [2022-11-30 09:14:53,706] [INFO] [utils.py:828:see_memory_usage] MA 4.22 GB Max_MA 4.22 GB CA 5.44 GB Max_CA 5 GB + 0: [2022-11-30 09:14:53,706] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 39.95 GB, percent = 7.9% +30: Time to load utils op: 0.11031579971313477 seconds +30: Time to load utils op: 0.1103360652923584 seconds +30: Time to load utils op: 0.1103525161743164 seconds +30: Time to load utils op: 0.11036443710327148 seconds +30: Time to load utils op: 0.11038565635681152 seconds +30: Time to load utils op: 0.11038994789123535 seconds +30: Time to load utils op: 0.11039376258850098 secondsTime to load utils op: 0.11039924621582031 seconds +30: +31: Time to load utils op: 0.11028051376342773 seconds +31: Time to load utils op: 0.11031508445739746 seconds +31: Time to load utils op: 0.11033797264099121 secondsTime to load utils op: 0.11034464836120605 seconds +31: +31: Time to load utils op: 0.11034440994262695 seconds +31: Time to load utils op: 0.11035776138305664 secondsTime to load utils op: 0.1103520393371582 seconds +31: +31: Time to load utils op: 0.11037325859069824 seconds + 0: Time to load utils op: 0.0006253719329833984 seconds +13: Time to load utils op: 0.3033735752105713 seconds + 0: [2022-11-30 09:14:53,744] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 + 0: [2022-11-30 09:14:53,744] [INFO] [utils.py:828:see_memory_usage] MA 6.14 GB Max_MA 6.14 GB CA 8.31 GB Max_CA 8 GB +11: Time to load utils op: 0.31105923652648926 seconds + 0: [2022-11-30 09:14:53,745] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 39.97 GB, percent = 7.9% + 9: Time to load utils op: 0.0008633136749267578 seconds + 9: Time to load utils op: 0.0012407302856445312 seconds + 9: Time to load utils op: 0.0013248920440673828 secondsTime to load utils op: 0.001302480697631836 secondsTime to load utils op: 0.0013179779052734375 seconds + 9: Time to load utils op: 0.0013005733489990234 seconds + 9: + 9: + 9: Time to load utils op: 0.0013155937194824219 seconds + 9: Time to load utils op: 0.0013136863708496094 seconds + 0: Time to load utils op: 0.2025160789489746 seconds + 0: Time to load utils op: 0.20196938514709473 seconds + 0: Time to load utils op: 0.2021021842956543 seconds + 0: Time to load utils op: 0.2017652988433838 seconds + 0: Time to load utils op: 0.20186448097229004 seconds + 0: Time to load utils op: 0.201873779296875 seconds +20: Time to load utils op: 0.0010981559753417969 seconds +20: Time to load utils op: 0.0011432170867919922 seconds +20: Time to load utils op: 0.0012311935424804688 seconds +20: Time to load utils op: 0.0013685226440429688 seconds +20: Time to load utils op: 0.0014140605926513672 secondsTime to load utils op: 0.0014319419860839844 seconds +20: +20: Time to load utils op: 0.0013833045959472656 seconds +20: Time to load utils op: 0.0014455318450927734 seconds +10: Time to load utils op: 0.0007960796356201172 seconds +10: Time to load utils op: 0.0011377334594726562 seconds +10: Time to load utils op: 0.0011439323425292969 seconds +12: Time to load utils op: 0.0012247562408447266 seconds +10: Time to load utils op: 0.0014028549194335938 secondsTime to load utils op: 0.001360177993774414 seconds +10: +10: Time to load utils op: 0.0014312267303466797 seconds +10: Time to load utils op: 0.001367807388305664 seconds +12: Time to load utils op: 0.0014598369598388672 seconds +10: Time to load utils op: 0.0014405250549316406 seconds +12: Time to load utils op: 0.0015451908111572266 seconds +12: Time to load utils op: 0.0015704631805419922 secondsTime to load utils op: 0.0015225410461425781 seconds +12: +12: Time to load utils op: 0.001537322998046875 seconds +12: Time to load utils op: 0.0015895366668701172 seconds +14: Time to load utils op: 0.0010685920715332031 seconds +12: Time to load utils op: 0.0014805793762207031 seconds +14: Time to load utils op: 0.001279592514038086 seconds +18: Time to load utils op: 0.0005812644958496094 seconds +18: Time to load utils op: 0.0004680156707763672 seconds +18: Time to load utils op: 0.0005919933319091797 seconds +14: Time to load utils op: 0.0013606548309326172 seconds +14: Time to load utils op: 0.0015001296997070312 secondsTime to load utils op: 0.0014772415161132812 seconds +18: Time to load utils op: 0.00045490264892578125 seconds +18: Time to load utils op: 0.0006659030914306641 seconds +14: +18: Time to load utils op: 0.0006816387176513672 seconds +18: Time to load utils op: 0.0006716251373291016 seconds +14: Time to load utils op: 0.001384735107421875 seconds +14: Time to load utils op: 0.00145721435546875 seconds +18: Time to load utils op: 0.0007429122924804688 seconds +14: Time to load utils op: 0.001497030258178711 seconds +23: Time to load utils op: 0.0005338191986083984 seconds +21: Time to load utils op: 0.0009529590606689453 secondsTime to load utils op: 0.0009057521820068359 seconds +21: +23: Time to load utils op: 0.0005674362182617188 seconds +23: Time to load utils op: 0.0006055831909179688 seconds +16: Time to load utils op: 0.0010466575622558594 seconds +23: Time to load utils op: 0.00042724609375 seconds +23: Time to load utils op: 0.0005636215209960938 seconds +16: Time to load utils op: 0.001306295394897461 seconds +16: Time to load utils op: 0.0012822151184082031 seconds +23: Time to load utils op: 0.0005815029144287109 seconds +23: Time to load utils op: 0.0006074905395507812 seconds +21: Time to load utils op: 0.0013554096221923828 secondsTime to load utils op: 0.001325845718383789 seconds +21: +23: Time to load utils op: 0.0006563663482666016 seconds +21: Time to load utils op: 0.0013113021850585938 seconds +16: Time to load utils op: 0.0013911724090576172 seconds +16: Time to load utils op: 0.0014920234680175781 secondsTime to load utils op: 0.0014314651489257812 seconds +16: +21: Time to load utils op: 0.0012049674987792969 seconds +16: Time to load utils op: 0.0013871192932128906 seconds +21: Time to load utils op: 0.001214742660522461 seconds +16: Time to load utils op: 0.0015079975128173828 seconds +21: Time to load utils op: 0.0013580322265625 seconds +15: Time to load utils op: 0.001149892807006836 seconds +13: Time to load utils op: 0.0005142688751220703 seconds +13: Time to load utils op: 0.0004487037658691406 secondsTime to load utils op: 0.00045180320739746094 seconds +13: +17: Time to load utils op: 0.0008020401000976562 seconds +13: Time to load utils op: 0.00042700767517089844 seconds +13: Time to load utils op: 0.0004315376281738281 seconds +15: Time to load utils op: 0.0013871192932128906 seconds +15: Time to load utils op: 0.00141143798828125 secondsTime to load utils op: 0.001331329345703125 seconds +15: +13: Time to load utils op: 0.0005934238433837891 secondsTime to load utils op: 0.0006089210510253906 seconds +13: +17: Time to load utils op: 0.0009419918060302734 seconds +15: Time to load utils op: 0.0015418529510498047 secondsTime to load utils op: 0.0015249252319335938 seconds +15: +15: Time to load utils op: 0.0013990402221679688 seconds +13: Time to load utils op: 0.0005993843078613281 seconds +15: Time to load utils op: 0.0015642642974853516 seconds +17: Time to load utils op: 0.0009307861328125 seconds +17: Time to load utils op: 0.0008127689361572266 seconds +25: Time to load utils op: 0.0009207725524902344 seconds +17: Time to load utils op: 0.0010752677917480469 seconds +17: Time to load utils op: 0.0010862350463867188 seconds +17: Time to load utils op: 0.0011162757873535156 seconds +25: Time to load utils op: 0.001214742660522461 seconds +17: Time to load utils op: 0.0011529922485351562 seconds +22: Time to load utils op: 0.0006954669952392578 seconds +25: Time to load utils op: 0.001371145248413086 seconds +25: Time to load utils op: 0.0013790130615234375 secondsTime to load utils op: 0.0011310577392578125 seconds +25: +24: Time to load utils op: 0.0005483627319335938 seconds +25: Time to load utils op: 0.0013072490692138672 seconds +25: Time to load utils op: 0.0013818740844726562 seconds +24: Time to load utils op: 0.0005724430084228516 secondsTime to load utils op: 0.0005984306335449219 seconds +24: +25: Time to load utils op: 0.001325368881225586 seconds +24: Time to load utils op: 0.0004558563232421875 seconds +24: Time to load utils op: 0.0004711151123046875 seconds +19: Time to load utils op: 0.001428365707397461 secondsTime to load utils op: 0.0014379024505615234 seconds +19: +24: Time to load utils op: 0.0005726814270019531 secondsTime to load utils op: 0.0005414485931396484 seconds +24: +24: Time to load utils op: 0.0005905628204345703 seconds +22: Time to load utils op: 0.0013141632080078125 seconds +22: Time to load utils op: 0.0013294219970703125 seconds +19: Time to load utils op: 0.0015327930450439453 secondsTime to load utils op: 0.0015530586242675781 seconds +19: +19: Time to load utils op: 0.0015587806701660156 secondsTime to load utils op: 0.0015528202056884766 seconds +19: +19: Time to load utils op: 0.0015225410461425781 seconds +19: Time to load utils op: 0.0016207695007324219 seconds +22: Time to load utils op: 0.001451730728149414 secondsTime to load utils op: 0.0015153884887695312 seconds +22: Time to load utils op: 0.0014977455139160156 seconds +22: +22: Time to load utils op: 0.0015869140625 seconds +22: Time to load utils op: 0.0016083717346191406 seconds +27: Time to load utils op: 0.0010287761688232422 seconds +27: Time to load utils op: 0.0010538101196289062 seconds +27: Time to load utils op: 0.0012767314910888672 seconds +27: Time to load utils op: 0.0012688636779785156 seconds +27: Time to load utils op: 0.0011227130889892578 seconds +27: Time to load utils op: 0.0012061595916748047 seconds +27: Time to load utils op: 0.0011739730834960938 seconds +27: Time to load utils op: 0.0012867450714111328 seconds +11: Time to load utils op: 0.20299935340881348 seconds +11: Time to load utils op: 0.20206212997436523 seconds +11: Time to load utils op: 0.20236849784851074 seconds +26: Time to load utils op: 0.0009109973907470703 seconds +11: Time to load utils op: 0.20249629020690918 seconds +11: Time to load utils op: 0.2025599479675293 seconds +11: Time to load utils op: 0.20277166366577148 seconds +26: Time to load utils op: 0.0010111331939697266 seconds +11: Time to load utils op: 0.20269370079040527 seconds +26: Time to load utils op: 0.0009946823120117188 seconds +26: Time to load utils op: 0.0012149810791015625 seconds +26: Time to load utils op: 0.0012176036834716797 seconds +26: Time to load utils op: 0.0012028217315673828 secondsTime to load utils op: 0.0014083385467529297 seconds +26: +26: Time to load utils op: 0.001188039779663086 seconds + 1: Time to load utils op: 0.21219921112060547 seconds + 7: Time to load utils op: 0.0011382102966308594 seconds + 1: Time to load utils op: 0.21220970153808594 seconds + 1: Time to load utils op: 0.2122337818145752 secondsTime to load utils op: 0.21223735809326172 seconds + 1: + 1: Time to load utils op: 0.2122488021850586 secondsTime to load utils op: 0.21225357055664062 seconds + 1: + 1: Time to load utils op: 0.2122654914855957 seconds + 2: Time to load utils op: 0.21223068237304688 seconds + 2: Time to load utils op: 0.21224117279052734 seconds + 7: Time to load utils op: 0.0013010501861572266 seconds + 7: Time to load utils op: 0.001432180404663086 seconds + 1: Time to load utils op: 0.21228504180908203 seconds + 2: Time to load utils op: 0.21230697631835938 seconds + 7: Time to load utils op: 0.001554250717163086 seconds + 2: Time to load utils op: 0.2123262882232666 seconds + 2: Time to load utils op: 0.2123243808746338 seconds + 2: Time to load utils op: 0.21233868598937988 secondsTime to load utils op: 0.21234655380249023 seconds + 2: + 2: Time to load utils op: 0.21236205101013184 seconds + 7: Time to load utils op: 0.0017380714416503906 secondsTime to load utils op: 0.001600503921508789 seconds + 7: + 7: Time to load utils op: 0.0015788078308105469 seconds + 7: Time to load utils op: 0.0016863346099853516 seconds + 4: Time to load utils op: 0.2103738784790039 seconds + 4: Time to load utils op: 0.21038389205932617 seconds + 4: Time to load utils op: 0.21041011810302734 seconds + 4: Time to load utils op: 0.21041154861450195 seconds + 4: Time to load utils op: 0.21042633056640625 seconds + 4: Time to load utils op: 0.2104344367980957 seconds + 4: Time to load utils op: 0.21043729782104492 secondsTime to load utils op: 0.21043825149536133 seconds + 4: +30: Time to load utils op: 0.001161336898803711 seconds +30: Time to load utils op: 0.0013132095336914062 seconds +30: Time to load utils op: 0.001279592514038086 seconds + 5: Time to load utils op: 0.21119427680969238 seconds +30: Time to load utils op: 0.0015842914581298828 seconds +30: Time to load utils op: 0.0015909671783447266 seconds +29: Time to load utils op: 0.0005822181701660156 seconds + 5: Time to load utils op: 0.21121501922607422 seconds + 5: Time to load utils op: 0.21125125885009766 seconds + 5: Time to load utils op: 0.2112562656402588 seconds +30: Time to load utils op: 0.001584768295288086 seconds + 5: Time to load utils op: 0.2112596035003662 seconds +30: Time to load utils op: 0.001543283462524414 seconds + 5: Time to load utils op: 0.21127939224243164 seconds +29: Time to load utils op: 0.0003986358642578125 seconds + 5: Time to load utils op: 0.21126723289489746 secondsTime to load utils op: 0.2112729549407959 seconds + 5: +30: Time to load utils op: 0.0015673637390136719 seconds +29: Time to load utils op: 0.0005266666412353516 seconds +29: Time to load utils op: 0.0004191398620605469 seconds +29: Time to load utils op: 0.0004665851593017578 seconds +29: Time to load utils op: 0.0004527568817138672 seconds +29: Time to load utils op: 0.000484466552734375 seconds +29: Time to load utils op: 0.0004532337188720703 seconds + 3: Time to load utils op: 0.21362948417663574 seconds + 3: Time to load utils op: 0.21362733840942383 seconds + 3: Time to load utils op: 0.2136826515197754 secondsTime to load utils op: 0.21368837356567383 seconds + 3: + 3: Time to load utils op: 0.2136847972869873 seconds + 3: Time to load utils op: 0.21370315551757812 seconds +31: Time to load utils op: 0.0010368824005126953 seconds +31: Time to load utils op: 0.0010750293731689453 seconds + 3: Time to load utils op: 0.2137000560760498 seconds + 3: Time to load utils op: 0.21371841430664062 seconds +31: Time to load utils op: 0.0012183189392089844 seconds +31: Time to load utils op: 0.0013325214385986328 seconds +31: Time to load utils op: 0.0013842582702636719 seconds +31: Time to load utils op: 0.0012962818145751953 secondsTime to load utils op: 0.0013930797576904297 seconds +31: + 6: Time to load utils op: 0.21119999885559082 seconds +31: Time to load utils op: 0.0014879703521728516 seconds + 6: Time to load utils op: 0.21123790740966797 seconds + 6: Time to load utils op: 0.21123981475830078 seconds + 6: Time to load utils op: 0.21125459671020508 seconds + 6: Time to load utils op: 0.21126770973205566 seconds + 6: Time to load utils op: 0.21126008033752441 seconds + 6: Time to load utils op: 0.21126294136047363 seconds + 6: Time to load utils op: 0.21126437187194824 seconds + 8: Time to load utils op: 0.2112712860107422 seconds + 8: Time to load utils op: 0.21127724647521973 seconds + 8: Time to load utils op: 0.21128058433532715 seconds + 8: Time to load utils op: 0.21129775047302246 seconds + 8: Time to load utils op: 0.21129846572875977 seconds + 8: Time to load utils op: 0.21130657196044922 seconds + 8: Time to load utils op: 0.21131324768066406 secondsTime to load utils op: 0.21131372451782227 seconds + 8: + 0: [2022-11-30 09:14:53,784] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 + 0: Time to load utils op: 0.00046062469482421875 seconds + 0: [2022-11-30 09:14:53,785] [INFO] [utils.py:828:see_memory_usage] MA 6.14 GB Max_MA 6.14 GB CA 8.31 GB Max_CA 8 GB + 0: Time to load utils op: 0.00040411949157714844 seconds + 0: Time to load utils op: 0.00040030479431152344 seconds + 0: [2022-11-30 09:14:53,785] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 39.98 GB, percent = 7.9% + 0: Time to load utils op: 0.0004036426544189453 seconds + 0: Time to load utils op: 0.0003952980041503906 seconds + 0: Time to load utils op: 0.0003864765167236328 seconds +11: Time to load utils op: 0.0005486011505126953 seconds +11: Time to load utils op: 0.00042939186096191406 seconds +11: Time to load utils op: 0.00035881996154785156 seconds +11: Time to load utils op: 0.00037407875061035156 seconds +11: Time to load utils op: 0.00040149688720703125 seconds +11: Time to load utils op: 0.0003783702850341797 seconds +11: Time to load utils op: 0.00037980079650878906 seconds +11: Time to load utils op: 0.00038933753967285156 seconds +28: Time to load utils op: 0.0004992485046386719 seconds +28: Time to load utils op: 0.00047850608825683594 secondsTime to load utils op: 0.0004780292510986328 seconds +28: +28: Time to load utils op: 0.00048422813415527344 seconds +28: Time to load utils op: 0.0005049705505371094 seconds +28: Time to load utils op: 0.0005519390106201172 seconds +28: Time to load utils op: 0.0005993843078613281 secondsTime to load utils op: 0.0005595684051513672 seconds +28: + 1: Time to load utils op: 0.0008940696716308594 seconds + 2: Time to load utils op: 0.0013644695281982422 seconds + 4: Time to load utils op: 0.001062631607055664 seconds + 1: Time to load utils op: 0.0014493465423583984 seconds + 1: Time to load utils op: 0.0013625621795654297 seconds + 1: Time to load utils op: 0.0014333724975585938 seconds + 1: Time to load utils op: 0.0014863014221191406 seconds + 1: Time to load utils op: 0.0014586448669433594 seconds + 4: Time to load utils op: 0.0009989738464355469 seconds + 1: Time to load utils op: 0.0013880729675292969 seconds + 1: Time to load utils op: 0.001508474349975586 seconds + 2: Time to load utils op: 0.0015676021575927734 seconds + 4: Time to load utils op: 0.0012562274932861328 seconds + 4: Time to load utils op: 0.0014111995697021484 secondsTime to load utils op: 0.0012021064758300781 seconds + 4: + 2: Time to load utils op: 0.0015108585357666016 secondsTime to load utils op: 0.0015795230865478516 seconds + 2: + 2: Time to load utils op: 0.0015439987182617188 seconds + 2: Time to load utils op: 0.0016102790832519531 seconds + 5: Time to load utils op: 0.0013246536254882812 seconds + 2: Time to load utils op: 0.0015711784362792969 seconds + 4: Time to load utils op: 0.001435995101928711 secondsTime to load utils op: 0.0013899803161621094 seconds + 4: + 2: Time to load utils op: 0.0016431808471679688 seconds + 4: Time to load utils op: 0.001447916030883789 seconds + 5: Time to load utils op: 0.0014522075653076172 seconds + 5: Time to load utils op: 0.0014259815216064453 seconds + 0: [2022-11-30 09:14:53,831] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 + 5: Time to load utils op: 0.0014567375183105469 secondsTime to load utils op: 0.0014667510986328125 seconds + 5: + 5: Time to load utils op: 0.0014638900756835938 seconds + 5: Time to load utils op: 0.0014705657958984375 seconds + 0: [2022-11-30 09:14:53,831] [INFO] [utils.py:828:see_memory_usage] MA 6.14 GB Max_MA 6.14 GB CA 8.31 GB Max_CA 8 GB + 0: [2022-11-30 09:14:53,831] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.11 GB, percent = 8.0% + 6: Time to load utils op: 0.0010976791381835938 seconds + 6: Time to load utils op: 0.0010733604431152344 seconds + 6: Time to load utils op: 0.0013742446899414062 seconds + 6: Time to load utils op: 0.0014808177947998047 seconds + 6: Time to load utils op: 0.0014491081237792969 seconds + 6: Time to load utils op: 0.001470327377319336 seconds + 6: Time to load utils op: 0.0014801025390625 seconds + 6: Time to load utils op: 0.0015740394592285156 seconds + 3: Time to load utils op: 0.0005381107330322266 secondsTime to load utils op: 0.0008263587951660156 seconds + 3: + 3: Time to load utils op: 0.000560760498046875 seconds + 3: Time to load utils op: 0.0005242824554443359 seconds + 3: Time to load utils op: 0.0006368160247802734 seconds + 3: Time to load utils op: 0.0005548000335693359 secondsTime to load utils op: 0.0005435943603515625 seconds + 3: + 3: Time to load utils op: 0.0005357265472412109 seconds + 8: Time to load utils op: 0.0009324550628662109 seconds + 8: Time to load utils op: 0.0008130073547363281 seconds + 8: Time to load utils op: 0.0008361339569091797 seconds + 8: Time to load utils op: 0.0011167526245117188 seconds + 8: Time to load utils op: 0.001054525375366211 seconds + 8: Time to load utils op: 0.0011057853698730469 seconds + 8: Time to load utils op: 0.0012662410736083984 seconds + 8: Time to load utils op: 0.0012612342834472656 seconds + 0: [2022-11-30 09:14:53,867] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer + 0: [2022-11-30 09:14:53,867] [INFO] [utils.py:828:see_memory_usage] MA 6.14 GB Max_MA 6.14 GB CA 8.31 GB Max_CA 8 GB + 0: [2022-11-30 09:14:53,868] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.11 GB, percent = 8.0% + 5: Time to load utils op: 0.0015041828155517578 seconds + 0: [2022-11-30 09:14:53,905] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer + 0: [2022-11-30 09:14:53,906] [INFO] [utils.py:828:see_memory_usage] MA 6.17 GB Max_MA 6.17 GB CA 8.31 GB Max_CA 8 GB + 0: [2022-11-30 09:14:53,906] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.11 GB, percent = 8.0% + 0: [2022-11-30 09:14:53,939] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer + 0: [2022-11-30 09:14:53,939] [INFO] [utils.py:828:see_memory_usage] MA 6.17 GB Max_MA 6.17 GB CA 8.31 GB Max_CA 8 GB + 0: [2022-11-30 09:14:53,939] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.11 GB, percent = 8.0% + 0: [2022-11-30 09:14:53,939] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam + 0: [2022-11-30 09:14:53,940] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler + 0: [2022-11-30 09:14:53,940] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = + 0: [2022-11-30 09:14:53,940] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: [2022-11-30 09:14:53,940] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: + 0: [2022-11-30 09:14:53,940] [INFO] [config.py:1011:print] activation_checkpointing_config { + 0: "partition_activations": false, + 0: "contiguous_memory_optimization": false, + 0: "cpu_checkpointing": false, + 0: "number_checkpoints": null, + 0: "synchronize_checkpoint_boundary": false, + 0: "profile": false + 0: } + 0: [2022-11-30 09:14:53,940] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] amp_enabled .................. False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] amp_params ................... False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] autotuning_config ............ { + 0: "enabled": false, + 0: "start_step": null, + 0: "end_step": null, + 0: "metric_path": null, + 0: "arg_mappings": null, + 0: "metric": "throughput", + 0: "model_info": null, + 0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", + 0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", + 0: "overwrite": true, + 0: "fast": true, + 0: "start_profile_step": 3, + 0: "end_profile_step": 5, + 0: "tuner_type": "gridsearch", + 0: "tuner_early_stopping": 5, + 0: "tuner_num_trials": 50, + 0: "model_info_path": null, + 0: "mp_size": 1, + 0: "max_train_batch_size": null, + 0: "min_train_batch_size": 1, + 0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, + 0: "min_train_micro_batch_size_per_gpu": 1, + 0: "num_tuning_micro_batch_sizes": 3 + 0: } + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] bfloat16_enabled ............. True + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] comms_config ................. + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] communication_data_type ...... None + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa + 0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] curriculum_enabled ........... False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] curriculum_params ............ False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] dataloader_drop_last ......... False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] disable_allgather ............ False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] dump_state ................... False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] elasticity_enabled ........... False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] flops_profiler_config ........ { + 0: "enabled": false, + 0: "profile_step": 1, + 0: "module_depth": -1, + 0: "top_modules": 1, + 0: "detailed": true, + 0: "output_file": null + 0: } + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] fp16_auto_cast ............... None + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] fp16_enabled ................. False + 0: [2022-11-30 09:14:53,941] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] global_rank .................. 0 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] load_universal_checkpoint .... False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] loss_scale ................... 1.0 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] memory_breakdown ............. False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] monitor_config ............... + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] nebula_config ................ { + 0: "enabled": false, + 0: "persistent_storage_path": null, + 0: "persistent_time_interval": 100, + 0: "num_of_version_in_retention": 2, + 0: "enable_nebula_load": true, + 0: "load_path": null + 0: } + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] optimizer_name ............... None + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] optimizer_params ............. None + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] pld_enabled .................. False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] pld_params ................... False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] prescale_gradients ........... False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] scheduler_name ............... None + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] scheduler_params ............. None + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] sparse_attention ............. None + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] steps_per_print .............. 2000 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] train_batch_size ............. 256 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 1 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] use_node_local_storage ....... False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] world_size ................... 256 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] zero_enabled ................. False + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 + 0: [2022-11-30 09:14:53,942] [INFO] [config.py:996:print_user_config] json = { + 0: "train_micro_batch_size_per_gpu": 1, + 0: "train_batch_size": 256, + 0: "gradient_clipping": 1.0, + 0: "zero_optimization": { + 0: "stage": 0 + 0: }, + 0: "bf16": { + 0: "enabled": true + 0: }, + 0: "steps_per_print": 2.000000e+03, + 0: "wall_clock_breakdown": false + 0: } + 0: Time to load utils op: 0.000457763671875 seconds + 0: [2022-11-30 09:14:53,943] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=1 + 0: [2022-11-30 09:14:53,966] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=33 [0, 33) STAGE_PARAMS=1096338432 (1096.338M) TOTAL_PARAMS=1096338432 (1096.338M) UNIQUE_PARAMS=1096338432 (1096.338M) +24: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: WARNING: could not find the metadata file checkpoints_1b121b +28: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: will not load any checkpoints and will start from random + 0: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-30 09:14:53,972] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-30 09:14:53,973] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-30 09:14:53,975] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-30 09:14:53,974] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-30 09:14:53,975] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b121b/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: time (ms) | load-checkpoint: 9.03 + 0: estimated model parameters: 1.096338432 + 0: estimated model parameters without embeddings: 1.002523648 + 0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-11-30 09:14:54 + 0: > building train, validation, and test datasets ... + 0: > datasets target sizes (minimum size): + 0: train: 10156250 + 0: validation: 10240 + 0: test: 256 + 0: > building train, validation, and test datasets for GPT ... + 0: > building dataset index ... + 0: reading sizes... + 0: reading pointers... + 0: reading document index... + 0: creating numpy buffer of mmap... + 0: creating memory view of numpy buffer... + 0: > finished creating indexed dataset in 0.021867 seconds + 0: number of documents: 210604984 + 0: > dataset split: + 0: train: + 0: document indices in [0, 199864130) total of 199864130 documents + 0: validation: + 0: document indices in [199864130, 210394379) total of 10530249 documents + 0: test: + 0: document indices in [210394379, 210604984) total of 210605 documents + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_10156250ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_10156250ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_10156250ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.052 seconds + 0: total number of samples: 173377817 + 0: total number of epochs: 1 + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_10240ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_10240ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_10240ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.017 seconds + 0: total number of samples: 9118345 + 0: total number of epochs: 1 + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.010 seconds + 0: total number of samples: 182928 + 0: total number of epochs: 1 + 0: > finished creating GPT datasets ... + 0: [after dataloaders are built] datetime: 2022-11-30 09:15:15 + 0: done with setup ... + 0: training ... + 0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +31: time (ms) | model-and-optimizer-setup: 32355.25 | train/valid/test-data-iterators-setup: 21342.28 + 0: [000-000] 1.0963B / 1.0025B + 0: [before the start of training step] datetime: 2022-11-30 09:15:15 + 0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 8825.99951171875 | max allocated: 22728.953125 | reserved: 24902.0 | max reserved: 24902.0 +31: iteration 10/ 39672 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 2.66 | learning rate: 5.041E-06 | global batch size: 256 | lm loss: 1.023746E+01 | grad norm: 23.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.298 | TFLOPs: 5.83 | +31: iteration 20/ 39672 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 0.84 | learning rate: 1.008E-05 | global batch size: 256 | lm loss: 8.736498E+00 | grad norm: 3.663 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.434 | TFLOPs: 18.48 | +31: iteration 30/ 39672 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 0.85 | learning rate: 1.512E-05 | global batch size: 256 | lm loss: 8.334310E+00 | grad norm: 2.610 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.845 | TFLOPs: 18.32 | +31: iteration 40/ 39672 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 0.82 | learning rate: 2.016E-05 | global batch size: 256 | lm loss: 7.949557E+00 | grad norm: 3.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.737 | TFLOPs: 18.98 | +31: iteration 50/ 39672 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 0.80 | learning rate: 2.521E-05 | global batch size: 256 | lm loss: 7.563316E+00 | grad norm: 3.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.365 | TFLOPs: 19.44 | +31: iteration 60/ 39672 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 0.78 | learning rate: 3.025E-05 | global batch size: 256 | lm loss: 7.262939E+00 | grad norm: 3.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.369 | TFLOPs: 19.93 | +31: iteration 70/ 39672 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 0.78 | learning rate: 3.529E-05 | global batch size: 256 | lm loss: 6.991438E+00 | grad norm: 3.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.824 | TFLOPs: 19.83 | +31: iteration 80/ 39672 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 0.82 | learning rate: 4.033E-05 | global batch size: 256 | lm loss: 6.749185E+00 | grad norm: 2.659 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.931 | TFLOPs: 18.87 | +31: iteration 90/ 39672 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 0.75 | learning rate: 4.537E-05 | global batch size: 256 | lm loss: 6.613591E+00 | grad norm: 2.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.520 | TFLOPs: 20.72 | +31: iteration 100/ 39672 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 0.76 | learning rate: 5.041E-05 | global batch size: 256 | lm loss: 6.440133E+00 | grad norm: 2.434 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.526 | TFLOPs: 20.48 | +31: iteration 110/ 39672 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 0.78 | learning rate: 5.545E-05 | global batch size: 256 | lm loss: 6.304549E+00 | grad norm: 2.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.006 | TFLOPs: 19.78 | +31: iteration 120/ 39672 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 0.72 | learning rate: 6.049E-05 | global batch size: 256 | lm loss: 6.190597E+00 | grad norm: 2.787 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.976 | TFLOPs: 21.41 | +31: iteration 130/ 39672 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 0.73 | learning rate: 6.554E-05 | global batch size: 256 | lm loss: 6.074699E+00 | grad norm: 2.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.401 | TFLOPs: 21.20 | +31: iteration 140/ 39672 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 0.74 | learning rate: 7.058E-05 | global batch size: 256 | lm loss: 6.018138E+00 | grad norm: 2.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.481 | TFLOPs: 20.84 | +31: iteration 150/ 39672 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 0.74 | learning rate: 7.562E-05 | global batch size: 256 | lm loss: 5.956989E+00 | grad norm: 2.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.898 | TFLOPs: 21.05 | +31: iteration 160/ 39672 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 0.77 | learning rate: 8.066E-05 | global batch size: 256 | lm loss: 5.836029E+00 | grad norm: 1.750 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.851 | TFLOPs: 20.20 | +31: iteration 170/ 39672 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 0.74 | learning rate: 8.570E-05 | global batch size: 256 | lm loss: 5.821696E+00 | grad norm: 1.563 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.665 | TFLOPs: 20.85 | +31: iteration 180/ 39672 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 0.74 | learning rate: 9.074E-05 | global batch size: 256 | lm loss: 5.716129E+00 | grad norm: 1.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.665 | TFLOPs: 21.03 | +31: iteration 190/ 39672 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 0.77 | learning rate: 9.578E-05 | global batch size: 256 | lm loss: 5.683355E+00 | grad norm: 1.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.711 | TFLOPs: 20.19 | +31: iteration 200/ 39672 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 0.71 | learning rate: 1.008E-04 | global batch size: 256 | lm loss: 5.620704E+00 | grad norm: 1.633 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 358.639 | TFLOPs: 21.70 | +31: iteration 210/ 39672 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 0.77 | learning rate: 1.059E-04 | global batch size: 256 | lm loss: 5.589636E+00 | grad norm: 1.827 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.943 | TFLOPs: 20.08 | +31: iteration 220/ 39672 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 0.79 | learning rate: 1.109E-04 | global batch size: 256 | lm loss: 5.519827E+00 | grad norm: 1.482 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.403 | TFLOPs: 19.69 | +31: iteration 230/ 39672 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 0.72 | learning rate: 1.159E-04 | global batch size: 256 | lm loss: 5.490613E+00 | grad norm: 1.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.795 | TFLOPs: 21.46 | +31: iteration 240/ 39672 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 0.74 | learning rate: 1.210E-04 | global batch size: 256 | lm loss: 5.468011E+00 | grad norm: 1.874 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.344 | TFLOPs: 20.89 | +31: iteration 250/ 39672 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 0.78 | learning rate: 1.260E-04 | global batch size: 256 | lm loss: 5.395864E+00 | grad norm: 1.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.465 | TFLOPs: 19.93 | +31: iteration 260/ 39672 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 0.74 | learning rate: 1.311E-04 | global batch size: 256 | lm loss: 5.382565E+00 | grad norm: 1.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.306 | TFLOPs: 20.83 | +31: iteration 270/ 39672 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 0.74 | learning rate: 1.361E-04 | global batch size: 256 | lm loss: 5.302442E+00 | grad norm: 1.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.421 | TFLOPs: 21.02 | +31: iteration 280/ 39672 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 0.74 | learning rate: 1.412E-04 | global batch size: 256 | lm loss: 5.283850E+00 | grad norm: 1.082 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.448 | TFLOPs: 20.96 | +31: iteration 290/ 39672 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 0.78 | learning rate: 1.462E-04 | global batch size: 256 | lm loss: 5.224294E+00 | grad norm: 0.925 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.829 | TFLOPs: 19.83 | +31: iteration 300/ 39672 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 0.80 | learning rate: 1.512E-04 | global batch size: 256 | lm loss: 5.151413E+00 | grad norm: 1.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.163 | TFLOPs: 19.37 | +31: iteration 310/ 39672 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 0.76 | learning rate: 1.563E-04 | global batch size: 256 | lm loss: 5.164858E+00 | grad norm: 0.749 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.271 | TFLOPs: 20.34 | +31: iteration 320/ 39672 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 0.77 | learning rate: 1.613E-04 | global batch size: 256 | lm loss: 5.137189E+00 | grad norm: 1.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.282 | TFLOPs: 20.04 | +31: iteration 330/ 39672 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 0.73 | learning rate: 1.664E-04 | global batch size: 256 | lm loss: 5.107657E+00 | grad norm: 0.645 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.607 | TFLOPs: 21.21 | +31: iteration 340/ 39672 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 0.77 | learning rate: 1.714E-04 | global batch size: 256 | lm loss: 5.060718E+00 | grad norm: 1.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.592 | TFLOPs: 20.06 | +31: iteration 350/ 39672 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 0.79 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 5.017180E+00 | grad norm: 0.985 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.638 | TFLOPs: 19.64 | +31: iteration 360/ 39672 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 0.75 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 4.986292E+00 | grad norm: 0.805 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.053 | TFLOPs: 20.57 | +31: iteration 370/ 39672 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 0.76 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 4.907201E+00 | grad norm: 0.718 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.883 | TFLOPs: 20.44 | +31: iteration 380/ 39672 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 0.76 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 4.903831E+00 | grad norm: 0.713 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.364 | TFLOPs: 20.47 | +31: iteration 390/ 39672 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 0.78 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 4.832507E+00 | grad norm: 0.594 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.896 | TFLOPs: 19.84 | +31: iteration 400/ 39672 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 0.74 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.838090E+00 | grad norm: 0.978 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.729 | TFLOPs: 20.86 | +31: iteration 410/ 39672 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 0.81 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.816224E+00 | grad norm: 0.832 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.736 | TFLOPs: 19.04 | +31: iteration 420/ 39672 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 0.83 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.822580E+00 | grad norm: 0.801 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.860 | TFLOPs: 18.69 | +31: iteration 430/ 39672 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 0.82 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.725330E+00 | grad norm: 0.859 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.779 | TFLOPs: 18.86 | +31: iteration 440/ 39672 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 0.81 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.672955E+00 | grad norm: 0.823 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.742 | TFLOPs: 19.22 | +31: iteration 450/ 39672 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 0.77 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.659672E+00 | grad norm: 0.635 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.364 | TFLOPs: 19.99 | +31: iteration 460/ 39672 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 0.79 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.627063E+00 | grad norm: 0.599 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.027 | TFLOPs: 19.60 | +31: iteration 470/ 39672 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 0.81 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.585892E+00 | grad norm: 0.743 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.405 | TFLOPs: 19.08 | +31: iteration 480/ 39672 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 0.78 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.542466E+00 | grad norm: 0.598 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.493 | TFLOPs: 19.75 | +31: iteration 490/ 39672 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 0.79 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.464825E+00 | grad norm: 0.765 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.588 | TFLOPs: 19.64 | +31: iteration 500/ 39672 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 0.77 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.456642E+00 | grad norm: 0.627 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.106 | TFLOPs: 20.21 | +31: iteration 510/ 39672 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 0.79 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.425234E+00 | grad norm: 0.844 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.937 | TFLOPs: 19.54 | +31: iteration 520/ 39672 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 0.77 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.385862E+00 | grad norm: 0.820 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.599 | TFLOPs: 20.12 | +31: iteration 530/ 39672 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 0.80 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.307187E+00 | grad norm: 0.841 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.196 | TFLOPs: 19.37 | +31: iteration 540/ 39672 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 0.75 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.320740E+00 | grad norm: 0.765 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.962 | TFLOPs: 20.57 | +31: iteration 550/ 39672 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 0.73 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.267862E+00 | grad norm: 0.860 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.401 | TFLOPs: 21.26 | +31: iteration 560/ 39672 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 0.76 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.255674E+00 | grad norm: 0.920 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.128 | TFLOPs: 20.40 | +31: iteration 570/ 39672 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 0.77 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.177567E+00 | grad norm: 0.887 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.466 | TFLOPs: 20.17 | +31: iteration 580/ 39672 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 0.79 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.106960E+00 | grad norm: 0.945 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.965 | TFLOPs: 19.72 | +31: iteration 590/ 39672 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 0.75 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.010294E+00 | grad norm: 0.913 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.777 | TFLOPs: 20.74 | +31: iteration 600/ 39672 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 0.75 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.951685E+00 | grad norm: 0.822 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.233 | TFLOPs: 20.58 | +31: iteration 610/ 39672 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 0.79 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.892881E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.268 | TFLOPs: 19.50 | +31: iteration 620/ 39672 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 0.77 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.832062E+00 | grad norm: 0.514 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.343 | TFLOPs: 19.98 | +31: iteration 630/ 39672 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 0.79 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.844114E+00 | grad norm: 0.592 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.895 | TFLOPs: 19.72 | +31: iteration 640/ 39672 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 0.77 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.740325E+00 | grad norm: 0.592 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.933 | TFLOPs: 20.14 | +31: iteration 650/ 39672 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 0.79 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.733882E+00 | grad norm: 0.593 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.889 | TFLOPs: 19.65 | +31: iteration 660/ 39672 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 0.79 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.688956E+00 | grad norm: 0.647 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.266 | TFLOPs: 19.68 | +31: iteration 670/ 39672 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 0.82 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.611819E+00 | grad norm: 0.598 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.595 | TFLOPs: 18.91 | +31: iteration 680/ 39672 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 0.81 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.611094E+00 | grad norm: 0.451 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.253 | TFLOPs: 19.19 | +31: iteration 690/ 39672 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 0.79 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.599461E+00 | grad norm: 0.500 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.774 | TFLOPs: 19.59 | +31: iteration 700/ 39672 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 0.82 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.582797E+00 | grad norm: 0.553 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.496 | TFLOPs: 18.78 | +31: iteration 710/ 39672 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 0.80 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.558060E+00 | grad norm: 0.452 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.678 | TFLOPs: 19.34 | +31: iteration 720/ 39672 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 0.83 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.566519E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.355 | TFLOPs: 18.72 | +31: iteration 730/ 39672 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 0.75 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.533295E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.145 | TFLOPs: 20.52 | +31: iteration 740/ 39672 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 0.75 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.502273E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.601 | TFLOPs: 20.79 | +31: iteration 750/ 39672 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 0.77 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.459590E+00 | grad norm: 0.549 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.171 | TFLOPs: 20.22 | +31: iteration 760/ 39672 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 0.82 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.501287E+00 | grad norm: 0.445 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.880 | TFLOPs: 18.93 | +31: iteration 770/ 39672 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 0.81 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.494532E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.406 | TFLOPs: 19.14 | +31: iteration 780/ 39672 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 0.85 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.424440E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.559 | TFLOPs: 18.12 | +31: iteration 790/ 39672 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 0.79 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.401207E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.937 | TFLOPs: 19.60 | +31: iteration 800/ 39672 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 0.75 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.378944E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.955 | TFLOPs: 20.69 | +31: iteration 810/ 39672 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 0.78 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 3.365141E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.412 | TFLOPs: 19.93 | +31: iteration 820/ 39672 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 0.81 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.371603E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.961 | TFLOPs: 19.11 | +31: iteration 830/ 39672 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 0.83 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.387451E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.025 | TFLOPs: 18.76 | +31: iteration 840/ 39672 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 0.78 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.313160E+00 | grad norm: 0.555 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.964 | TFLOPs: 19.78 | +31: iteration 850/ 39672 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 0.86 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.326086E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.435 | TFLOPs: 18.05 | +31: iteration 860/ 39672 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 0.82 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.307481E+00 | grad norm: 0.618 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.323 | TFLOPs: 18.89 | +31: iteration 870/ 39672 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 0.82 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.335171E+00 | grad norm: 0.741 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.692 | TFLOPs: 18.98 | +31: iteration 880/ 39672 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 0.83 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.366434E+00 | grad norm: 0.627 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.581 | TFLOPs: 18.73 | +31: iteration 890/ 39672 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 0.84 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.309378E+00 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.172 | TFLOPs: 18.52 | +31: iteration 900/ 39672 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 0.82 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.275708E+00 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.636 | TFLOPs: 18.97 | +31: iteration 910/ 39672 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 0.83 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.295050E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.409 | TFLOPs: 18.72 | +31: iteration 920/ 39672 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 0.85 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.292988E+00 | grad norm: 0.552 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.233 | TFLOPs: 18.22 | +31: iteration 930/ 39672 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 0.83 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.249790E+00 | grad norm: 0.420 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.007 | TFLOPs: 18.75 | +31: iteration 940/ 39672 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 0.82 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.244118E+00 | grad norm: 0.466 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.926 | TFLOPs: 18.87 | +31: iteration 950/ 39672 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 0.76 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.250095E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.714 | TFLOPs: 20.25 | +31: iteration 960/ 39672 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 0.76 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.215214E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.664 | TFLOPs: 20.49 | +31: iteration 970/ 39672 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 0.81 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.215520E+00 | grad norm: 0.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.285 | TFLOPs: 19.19 | +31: iteration 980/ 39672 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 0.77 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.170911E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.673 | TFLOPs: 20.19 | +31: iteration 990/ 39672 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 0.83 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.180994E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.038 | TFLOPs: 18.64 | +31: iteration 1000/ 39672 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 0.84 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.166791E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.657 | TFLOPs: 18.43 | +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 1000 | lm loss value: 3.135314E+00 | lm loss PPL: 2.299585E+01 | +31: ------------------------------------------------------------------------------------------ +31: iteration 1010/ 39672 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 0.85 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.199303E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.098 | TFLOPs: 18.16 | +31: iteration 1020/ 39672 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 0.77 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.165067E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.570 | TFLOPs: 20.00 | +31: iteration 1030/ 39672 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 0.81 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.155592E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.891 | TFLOPs: 19.23 | +31: iteration 1040/ 39672 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 0.77 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.236353E+00 | grad norm: 0.925 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.417 | TFLOPs: 20.11 | +31: iteration 1050/ 39672 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 0.79 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.265368E+00 | grad norm: 0.694 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.760 | TFLOPs: 19.59 | +31: iteration 1060/ 39672 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 0.81 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.192058E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.167 | TFLOPs: 19.19 | +31: iteration 1070/ 39672 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 0.80 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.158603E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.459 | TFLOPs: 19.33 | +31: iteration 1080/ 39672 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 0.75 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.097815E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.860 | TFLOPs: 20.74 | +31: iteration 1090/ 39672 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 0.76 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.117579E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.670 | TFLOPs: 20.25 | +31: iteration 1100/ 39672 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 0.77 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.147427E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.956 | TFLOPs: 20.08 | +31: iteration 1110/ 39672 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 0.77 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 3.101519E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.349 | TFLOPs: 19.99 | +31: iteration 1120/ 39672 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 0.76 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.124590E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.163 | TFLOPs: 20.46 | +31: iteration 1130/ 39672 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 0.76 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.124028E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.125 | TFLOPs: 20.46 | +31: iteration 1140/ 39672 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 0.82 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.078644E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.581 | TFLOPs: 18.97 | +31: iteration 1150/ 39672 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 0.82 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.113541E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.672 | TFLOPs: 18.92 | +31: iteration 1160/ 39672 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 0.83 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.092617E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.596 | TFLOPs: 18.73 | +31: iteration 1170/ 39672 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 0.84 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.089572E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.072 | TFLOPs: 18.34 | +31: iteration 1180/ 39672 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 0.87 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.108467E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 293.792 | TFLOPs: 17.77 | +31: iteration 1190/ 39672 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 0.84 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.108899E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.123 | TFLOPs: 18.40 | +31: iteration 1200/ 39672 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 0.87 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.079613E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.679 | TFLOPs: 17.89 | +31: iteration 1210/ 39672 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 0.83 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.067131E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.925 | TFLOPs: 18.63 | +31: iteration 1220/ 39672 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 0.86 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.007965E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.195 | TFLOPs: 17.92 | +31: iteration 1230/ 39672 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 0.88 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.061732E+00 | grad norm: 0.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 289.943 | TFLOPs: 17.54 | +31: iteration 1240/ 39672 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 0.85 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.036391E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.660 | TFLOPs: 18.19 | +31: iteration 1250/ 39672 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 0.83 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.040526E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.794 | TFLOPs: 18.68 | +31: iteration 1260/ 39672 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 0.86 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 2.982680E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.507 | TFLOPs: 17.94 | +31: iteration 1270/ 39672 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 0.80 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.042416E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.802 | TFLOPs: 19.35 | +31: iteration 1280/ 39672 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 0.81 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.068856E+00 | grad norm: 0.490 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.603 | TFLOPs: 19.21 | +31: iteration 1290/ 39672 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 0.81 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 2.953345E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.365 | TFLOPs: 19.08 | +31: iteration 1300/ 39672 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 0.84 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 3.016613E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.062 | TFLOPs: 18.52 | +31: iteration 1310/ 39672 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 0.86 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 2.994704E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.648 | TFLOPs: 18.07 | +31: iteration 1320/ 39672 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 0.83 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 2.993458E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.444 | TFLOPs: 18.66 | +31: iteration 1330/ 39672 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 0.79 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.995314E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.060 | TFLOPs: 19.60 | +31: iteration 1340/ 39672 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 0.84 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.004330E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.454 | TFLOPs: 18.36 | +31: iteration 1350/ 39672 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 0.76 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.979013E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.296 | TFLOPs: 20.47 | +31: iteration 1360/ 39672 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 0.81 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.944268E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.453 | TFLOPs: 19.21 | +31: iteration 1370/ 39672 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 0.79 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.979081E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.047 | TFLOPs: 19.73 | +31: iteration 1380/ 39672 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 0.77 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.971941E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.686 | TFLOPs: 20.19 | +31: iteration 1390/ 39672 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 0.78 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.968703E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.480 | TFLOPs: 19.81 | +31: iteration 1400/ 39672 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 0.76 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.007604E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.856 | TFLOPs: 20.44 | +31: iteration 1410/ 39672 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 0.75 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.969923E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.134 | TFLOPs: 20.64 | +31: iteration 1420/ 39672 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 0.75 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.921343E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.900 | TFLOPs: 20.68 | +31: iteration 1430/ 39672 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 0.76 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.923950E+00 | grad norm: 0.420 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.827 | TFLOPs: 20.26 | +31: iteration 1440/ 39672 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 0.84 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.958231E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.162 | TFLOPs: 18.34 | +31: iteration 1450/ 39672 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 0.75 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.944202E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.763 | TFLOPs: 20.62 | +31: iteration 1460/ 39672 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 0.74 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.956602E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.354 | TFLOPs: 20.83 | +31: iteration 1470/ 39672 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 0.78 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.922443E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.931 | TFLOPs: 19.90 | +31: iteration 1480/ 39672 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 0.87 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.951949E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 293.472 | TFLOPs: 17.75 | +31: iteration 1490/ 39672 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 0.76 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 2.962799E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.680 | TFLOPs: 20.25 | +31: iteration 1500/ 39672 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 0.85 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.933611E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.961 | TFLOPs: 18.21 | +31: iteration 1510/ 39672 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 0.78 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.934945E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.444 | TFLOPs: 19.81 | +31: iteration 1520/ 39672 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 0.77 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.993447E+00 | grad norm: 0.985 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.088 | TFLOPs: 20.09 | +31: iteration 1530/ 39672 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 0.78 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.106254E+00 | grad norm: 2.909 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.669 | TFLOPs: 19.94 | +31: iteration 1540/ 39672 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 0.78 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.240474E+00 | grad norm: 2.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.863 | TFLOPs: 19.90 | +31: iteration 1550/ 39672 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 0.78 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.193471E+00 | grad norm: 1.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.255 | TFLOPs: 19.98 | +31: iteration 1560/ 39672 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 0.77 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.084879E+00 | grad norm: 0.525 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.614 | TFLOPs: 20.24 | +31: iteration 1570/ 39672 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 0.82 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.992598E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.030 | TFLOPs: 18.94 | +31: iteration 1580/ 39672 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 0.72 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.978168E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.145 | TFLOPs: 21.61 | +31: iteration 1590/ 39672 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 0.73 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.962917E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.649 | TFLOPs: 21.15 | +31: iteration 1600/ 39672 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 0.74 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.919751E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.087 | TFLOPs: 20.82 | +31: iteration 1610/ 39672 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 0.82 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.897977E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.230 | TFLOPs: 18.89 | +31: iteration 1620/ 39672 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 0.76 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.893172E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.783 | TFLOPs: 20.31 | +31: iteration 1630/ 39672 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 0.75 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.901878E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.729 | TFLOPs: 20.55 | +31: iteration 1640/ 39672 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 0.80 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 2.872911E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.841 | TFLOPs: 19.35 | +31: iteration 1650/ 39672 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 0.78 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.927334E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.764 | TFLOPs: 19.83 | +31: iteration 1660/ 39672 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 0.80 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.855208E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.308 | TFLOPs: 19.32 | +31: iteration 1670/ 39672 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 0.77 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.887246E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.452 | TFLOPs: 19.99 | +31: iteration 1680/ 39672 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 0.76 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.860860E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.672 | TFLOPs: 20.43 | +31: iteration 1690/ 39672 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 0.76 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.906786E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.269 | TFLOPs: 20.46 | +31: iteration 1700/ 39672 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 0.79 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.900038E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.686 | TFLOPs: 19.64 | +31: iteration 1710/ 39672 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 0.77 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.871235E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.930 | TFLOPs: 20.14 | +31: iteration 1720/ 39672 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 0.75 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.869825E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.392 | TFLOPs: 20.77 | +31: iteration 1730/ 39672 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 0.79 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.859157E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.448 | TFLOPs: 19.69 | +31: iteration 1740/ 39672 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 0.81 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.892012E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.172 | TFLOPs: 19.07 | +31: iteration 1750/ 39672 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 0.78 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.867268E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.620 | TFLOPs: 19.94 | +31: iteration 1760/ 39672 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 0.80 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.875903E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.177 | TFLOPs: 19.37 | +31: iteration 1770/ 39672 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 0.83 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 2.844338E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.791 | TFLOPs: 18.62 | +31: iteration 1780/ 39672 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 0.82 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.832865E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.203 | TFLOPs: 18.95 | +31: iteration 1790/ 39672 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 0.78 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.883125E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.640 | TFLOPs: 19.88 | +31: iteration 1800/ 39672 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 0.79 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.823512E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.391 | TFLOPs: 19.50 | +31: iteration 1810/ 39672 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 0.72 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.853602E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.264 | TFLOPs: 21.37 | +31: iteration 1820/ 39672 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 0.76 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.833539E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.861 | TFLOPs: 20.44 | +31: iteration 1830/ 39672 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 0.78 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.821699E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.250 | TFLOPs: 19.98 | +31: iteration 1840/ 39672 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 0.79 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.826136E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.472 | TFLOPs: 19.69 | +31: iteration 1850/ 39672 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 0.77 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.835887E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.336 | TFLOPs: 20.11 | +31: iteration 1860/ 39672 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 0.89 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.795992E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 286.569 | TFLOPs: 17.34 | +31: iteration 1870/ 39672 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 0.83 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.805054E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.590 | TFLOPs: 18.55 | +31: iteration 1880/ 39672 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 0.80 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.790127E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.231 | TFLOPs: 19.37 | +31: iteration 1890/ 39672 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 0.77 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.835961E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.711 | TFLOPs: 20.07 | +31: iteration 1900/ 39672 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 0.71 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 2.775850E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 358.246 | TFLOPs: 21.67 | +31: iteration 1910/ 39672 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 0.74 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.828031E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.540 | TFLOPs: 20.90 | +31: iteration 1920/ 39672 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 0.78 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.790839E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.398 | TFLOPs: 19.75 | +31: iteration 1930/ 39672 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 0.77 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.801865E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.071 | TFLOPs: 20.21 | +31: iteration 1940/ 39672 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 0.75 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.791827E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.921 | TFLOPs: 20.56 | +31: iteration 1950/ 39672 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 0.76 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.771336E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.657 | TFLOPs: 20.31 | +31: iteration 1960/ 39672 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 0.77 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.826037E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.539 | TFLOPs: 20.06 | +31: iteration 1970/ 39672 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 0.77 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.824813E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.718 | TFLOPs: 20.01 | +31: iteration 1980/ 39672 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 0.81 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.795902E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.429 | TFLOPs: 19.20 | +31: iteration 1990/ 39672 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 0.76 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.822196E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.885 | TFLOPs: 20.50 | + 0: [2022-11-30 09:41:50,030] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.0001992609515999032, 0.0001992609515999032, 0.0001992609515999032], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 2000/ 39672 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 0.79 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.811870E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.927 | TFLOPs: 19.66 | + 0: steps: 2000 loss: 2.8911 iter time (s): 0.794 samples/sec: 322.533 +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 2000 | lm loss value: 2.702859E+00 | lm loss PPL: 1.492234E+01 | +31: ------------------------------------------------------------------------------------------ +31: iteration 2010/ 39672 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 0.79 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 2.822247E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.392 | TFLOPs: 19.69 | +31: iteration 2020/ 39672 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 0.85 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 2.836804E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.945 | TFLOPs: 18.27 | +31: iteration 2030/ 39672 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 0.83 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 2.762823E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.399 | TFLOPs: 18.60 | +31: iteration 2040/ 39672 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 0.84 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 2.785978E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.369 | TFLOPs: 18.53 | +31: iteration 2050/ 39672 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 0.77 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 2.811582E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.348 | TFLOPs: 20.17 | +31: iteration 2060/ 39672 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 0.82 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 2.785000E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.035 | TFLOPs: 18.88 | +31: iteration 2070/ 39672 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 0.76 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 2.763266E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.476 | TFLOPs: 20.30 | +31: iteration 2080/ 39672 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 0.73 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 2.780961E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.540 | TFLOPs: 21.09 | +31: iteration 2090/ 39672 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 0.76 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 2.774908E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.851 | TFLOPs: 20.50 | +31: iteration 2100/ 39672 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 0.73 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 2.767776E+00 | grad norm: 0.478 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.546 | TFLOPs: 21.21 | +31: iteration 2110/ 39672 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 0.83 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 2.755839E+00 | grad norm: 0.799 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.027 | TFLOPs: 18.63 | +31: iteration 2120/ 39672 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 0.81 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 2.773098E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.492 | TFLOPs: 19.03 | +31: iteration 2130/ 39672 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 0.81 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 2.776721E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.994 | TFLOPs: 19.18 | +31: iteration 2140/ 39672 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 0.76 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 2.770796E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.916 | TFLOPs: 20.32 | +31: iteration 2150/ 39672 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 0.77 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 2.757508E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.446 | TFLOPs: 19.99 | +31: iteration 2160/ 39672 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 0.75 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 2.758335E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.315 | TFLOPs: 20.65 | +31: iteration 2170/ 39672 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 0.81 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 2.773035E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.074 | TFLOPs: 19.18 | +31: iteration 2180/ 39672 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 0.76 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 2.780329E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.756 | TFLOPs: 20.49 | +31: iteration 2190/ 39672 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 0.78 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 2.755197E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.840 | TFLOPs: 19.95 | +31: iteration 2200/ 39672 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 0.77 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 2.778805E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.874 | TFLOPs: 20.20 | +31: iteration 2210/ 39672 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 0.79 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 2.731465E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.507 | TFLOPs: 19.57 | +31: iteration 2220/ 39672 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 0.76 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 2.795035E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.204 | TFLOPs: 20.28 | +31: iteration 2230/ 39672 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 0.78 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 2.750695E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.791 | TFLOPs: 19.83 | +31: iteration 2240/ 39672 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 0.77 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 2.775032E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.549 | TFLOPs: 20.12 | +31: iteration 2250/ 39672 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 0.81 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 2.737375E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.073 | TFLOPs: 19.18 | +31: iteration 2260/ 39672 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 0.79 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 2.705547E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.536 | TFLOPs: 19.51 | +31: iteration 2270/ 39672 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 0.83 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 2.709394E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.304 | TFLOPs: 18.71 | +31: iteration 2280/ 39672 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 0.80 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 2.731539E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.418 | TFLOPs: 19.44 | +31: iteration 2290/ 39672 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 0.86 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 2.761398E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.742 | TFLOPs: 18.07 | +31: iteration 2300/ 39672 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 0.82 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 2.734093E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.897 | TFLOPs: 18.93 | +31: iteration 2310/ 39672 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 0.83 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 2.758153E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.469 | TFLOPs: 18.72 | +31: iteration 2320/ 39672 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 0.80 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 2.749328E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.046 | TFLOPs: 19.36 | +31: iteration 2330/ 39672 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 0.89 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 2.680097E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 287.012 | TFLOPs: 17.36 | +31: iteration 2340/ 39672 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 0.84 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 2.695263E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.601 | TFLOPs: 18.49 | +31: iteration 2350/ 39672 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 0.84 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 2.721539E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.245 | TFLOPs: 18.41 | +31: iteration 2360/ 39672 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 0.84 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 2.739268E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.417 | TFLOPs: 18.36 | +31: iteration 2370/ 39672 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 0.80 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 2.747839E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.295 | TFLOPs: 19.32 | +31: iteration 2380/ 39672 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 0.77 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 2.732822E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.262 | TFLOPs: 20.16 | +31: iteration 2390/ 39672 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 0.76 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 2.720486E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.759 | TFLOPs: 20.43 | +31: iteration 2400/ 39672 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 0.77 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 2.762313E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.798 | TFLOPs: 20.01 | +31: iteration 2410/ 39672 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 0.79 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 2.723108E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.356 | TFLOPs: 19.56 | +31: iteration 2420/ 39672 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 0.80 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 2.714338E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.784 | TFLOPs: 19.41 | +31: iteration 2430/ 39672 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 0.84 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 2.719745E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.748 | TFLOPs: 18.44 | +31: iteration 2440/ 39672 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 0.75 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 2.692651E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.997 | TFLOPs: 20.57 | +31: iteration 2450/ 39672 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 0.82 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 2.722085E+00 | grad norm: 1.610 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.016 | TFLOPs: 18.94 | +31: iteration 2460/ 39672 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 0.78 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.169517E+00 | grad norm: 3.846 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.665 | TFLOPs: 19.82 | +31: iteration 2470/ 39672 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 0.77 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.079206E+00 | grad norm: 4.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.594 | TFLOPs: 20.06 | +31: iteration 2480/ 39672 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 0.83 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 2.969612E+00 | grad norm: 1.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.074 | TFLOPs: 18.58 | +31: iteration 2490/ 39672 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 0.80 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 2.932240E+00 | grad norm: 0.714 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.388 | TFLOPs: 19.32 | +31: iteration 2500/ 39672 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 0.73 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 2.911366E+00 | grad norm: 0.697 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.756 | TFLOPs: 21.34 | +31: iteration 2510/ 39672 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 0.86 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 2.864813E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.100 | TFLOPs: 18.03 | +31: iteration 2520/ 39672 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 0.76 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 2.769458E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.984 | TFLOPs: 20.27 | +31: iteration 2530/ 39672 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 0.84 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 2.758570E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.216 | TFLOPs: 18.46 | +31: iteration 2540/ 39672 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 0.76 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 2.731139E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.089 | TFLOPs: 20.33 | +31: iteration 2550/ 39672 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 0.80 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 2.700152E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.727 | TFLOPs: 19.34 | +31: iteration 2560/ 39672 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 0.76 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 2.704620E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.474 | TFLOPs: 20.42 | +31: iteration 2570/ 39672 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 0.74 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 2.714594E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.794 | TFLOPs: 20.98 | +31: iteration 2580/ 39672 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 0.76 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 2.716609E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.159 | TFLOPs: 20.40 | +31: iteration 2590/ 39672 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 0.80 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 2.737236E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.479 | TFLOPs: 19.39 | +31: iteration 2600/ 39672 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 0.77 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 2.685057E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.096 | TFLOPs: 20.15 | +31: iteration 2610/ 39672 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 0.75 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 2.717151E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.557 | TFLOPs: 20.66 | +31: iteration 2620/ 39672 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 0.76 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 2.725024E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.486 | TFLOPs: 20.42 | +31: iteration 2630/ 39672 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 0.81 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 2.697704E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.264 | TFLOPs: 19.13 | +31: iteration 2640/ 39672 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 0.83 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 2.742565E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.872 | TFLOPs: 18.56 | +31: iteration 2650/ 39672 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 0.85 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 2.711256E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.629 | TFLOPs: 18.19 | +31: iteration 2660/ 39672 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 0.84 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 2.682820E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.285 | TFLOPs: 18.53 | +31: iteration 2670/ 39672 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 0.82 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 2.687567E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.074 | TFLOPs: 18.82 | +31: iteration 2680/ 39672 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 0.85 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 2.655001E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.382 | TFLOPs: 18.29 | +31: iteration 2690/ 39672 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 0.84 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 2.679261E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.012 | TFLOPs: 18.39 | +31: iteration 2700/ 39672 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 0.86 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 2.690039E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.294 | TFLOPs: 18.11 | +31: iteration 2710/ 39672 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 0.85 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 2.651492E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.479 | TFLOPs: 18.30 | +31: iteration 2720/ 39672 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 0.77 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 2.708446E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.886 | TFLOPs: 20.14 | +31: iteration 2730/ 39672 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 0.74 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 2.665950E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.538 | TFLOPs: 20.96 | +31: iteration 2740/ 39672 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 0.76 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 2.642854E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.009 | TFLOPs: 20.51 | +31: iteration 2750/ 39672 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 0.80 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 2.652467E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.210 | TFLOPs: 19.37 | +31: iteration 2760/ 39672 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 0.78 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 2.664138E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.589 | TFLOPs: 19.94 | +31: iteration 2770/ 39672 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 0.81 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 2.687782E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.265 | TFLOPs: 19.19 | +31: iteration 2780/ 39672 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 0.74 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 2.678402E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.928 | TFLOPs: 20.99 | +31: iteration 2790/ 39672 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 0.84 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 2.689671E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.304 | TFLOPs: 18.47 | +31: iteration 2800/ 39672 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 0.80 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 2.710358E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.030 | TFLOPs: 19.24 | +31: iteration 2810/ 39672 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 0.89 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 2.631417E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 289.158 | TFLOPs: 17.49 | +31: iteration 2820/ 39672 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 0.88 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 2.703414E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 291.471 | TFLOPs: 17.63 | +31: iteration 2830/ 39672 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 0.87 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 2.696024E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 294.860 | TFLOPs: 17.84 | +31: iteration 2840/ 39672 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 0.81 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 2.652118E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.270 | TFLOPs: 19.07 | +31: iteration 2850/ 39672 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 0.87 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 2.672212E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 294.319 | TFLOPs: 17.81 | +31: iteration 2860/ 39672 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 0.79 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 2.668205E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.747 | TFLOPs: 19.59 | +31: iteration 2870/ 39672 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 0.84 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 2.675837E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.457 | TFLOPs: 18.42 | +31: iteration 2880/ 39672 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 0.81 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 2.663987E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.741 | TFLOPs: 19.10 | +31: iteration 2890/ 39672 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 0.88 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 2.647242E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 290.643 | TFLOPs: 17.58 | +31: iteration 2900/ 39672 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 0.79 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 2.710271E+00 | grad norm: 0.629 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.074 | TFLOPs: 19.48 | +31: iteration 2910/ 39672 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 0.77 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 2.755076E+00 | grad norm: 0.612 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.896 | TFLOPs: 20.14 | +31: iteration 2920/ 39672 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 0.73 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 2.698315E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.783 | TFLOPs: 21.16 | +31: iteration 2930/ 39672 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 0.72 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 2.658072E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.399 | TFLOPs: 21.56 | +31: iteration 2940/ 39672 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 0.78 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 2.653300E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.039 | TFLOPs: 19.97 | +31: iteration 2950/ 39672 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 0.81 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 2.638237E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.458 | TFLOPs: 19.14 | +31: iteration 2960/ 39672 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 0.80 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 2.685580E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.231 | TFLOPs: 19.31 | +31: iteration 2970/ 39672 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 0.82 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 2.689077E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.207 | TFLOPs: 18.95 | +31: iteration 2980/ 39672 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 0.85 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 2.661752E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.481 | TFLOPs: 18.12 | +31: iteration 2990/ 39672 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 0.80 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 2.650267E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.306 | TFLOPs: 19.44 | +31: iteration 3000/ 39672 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 0.86 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 2.651972E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.297 | TFLOPs: 17.93 | +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 3000 | lm loss value: 2.601759E+00 | lm loss PPL: 1.348744E+01 | +31: ------------------------------------------------------------------------------------------ +31: iteration 3010/ 39672 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 0.80 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 2.632009E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.159 | TFLOPs: 19.31 | +31: iteration 3020/ 39672 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 0.79 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 2.649696E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.543 | TFLOPs: 19.51 | +31: iteration 3030/ 39672 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 0.77 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 2.607437E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.100 | TFLOPs: 20.03 | +31: iteration 3040/ 39672 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 0.80 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 2.644619E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.315 | TFLOPs: 19.26 | +31: iteration 3050/ 39672 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 0.72 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 2.650863E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.247 | TFLOPs: 21.49 | +31: iteration 3060/ 39672 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 0.77 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 2.668200E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.400 | TFLOPs: 20.17 | +31: iteration 3070/ 39672 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 0.84 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 2.669746E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.556 | TFLOPs: 18.49 | +31: iteration 3080/ 39672 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 0.75 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 2.638093E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.001 | TFLOPs: 20.75 | +31: iteration 3090/ 39672 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 0.75 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 2.637705E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.808 | TFLOPs: 20.68 | +31: iteration 3100/ 39672 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 0.78 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 2.667907E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.576 | TFLOPs: 19.94 | +31: iteration 3110/ 39672 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 0.84 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 2.604119E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.015 | TFLOPs: 18.39 | +31: iteration 3120/ 39672 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 0.79 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 2.645059E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.385 | TFLOPs: 19.62 | +31: iteration 3130/ 39672 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 0.73 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 2.636675E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.802 | TFLOPs: 21.10 | +31: iteration 3140/ 39672 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 0.77 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 2.610932E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.070 | TFLOPs: 20.21 | +31: iteration 3150/ 39672 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 0.75 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 2.657353E+00 | grad norm: 0.674 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.981 | TFLOPs: 20.63 | +31: iteration 3160/ 39672 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 0.81 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 2.630882E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.022 | TFLOPs: 19.06 | +31: iteration 3170/ 39672 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 0.81 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 2.631857E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.066 | TFLOPs: 19.06 | +31: iteration 3180/ 39672 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 0.83 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 2.643637E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.722 | TFLOPs: 18.68 | +31: iteration 3190/ 39672 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 0.88 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 2.597633E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 289.336 | TFLOPs: 17.50 | +31: iteration 3200/ 39672 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 0.84 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 2.601879E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.458 | TFLOPs: 18.42 | +31: iteration 3210/ 39672 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 0.84 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 2.648879E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.419 | TFLOPs: 18.48 | +31: iteration 3220/ 39672 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 0.83 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 2.607100E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.860 | TFLOPs: 18.62 | +31: iteration 3230/ 39672 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 0.83 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 2.631926E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.869 | TFLOPs: 18.75 | +31: iteration 3240/ 39672 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 0.76 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 2.608210E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.388 | TFLOPs: 20.35 | +31: iteration 3250/ 39672 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 0.82 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 2.629027E+00 | grad norm: 0.704 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.151 | TFLOPs: 18.82 | +31: iteration 3260/ 39672 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 0.79 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 2.685133E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.412 | TFLOPs: 19.51 | +31: iteration 3270/ 39672 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 0.79 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 2.647704E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.641 | TFLOPs: 19.70 | +31: iteration 3280/ 39672 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 0.78 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 2.625462E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.040 | TFLOPs: 19.79 | +31: iteration 3290/ 39672 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 0.79 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 2.596573E+00 | grad norm: 0.520 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.547 | TFLOPs: 19.57 | +31: iteration 3300/ 39672 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 0.75 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 2.805875E+00 | grad norm: 1.043 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.944 | TFLOPs: 20.63 | +31: iteration 3310/ 39672 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 0.76 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 2.728315E+00 | grad norm: 0.487 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.022 | TFLOPs: 20.51 | +31: iteration 3320/ 39672 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 0.78 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 2.694719E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.155 | TFLOPs: 19.85 | +31: iteration 3330/ 39672 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 0.81 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 2.681429E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.781 | TFLOPs: 19.16 | +31: iteration 3340/ 39672 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 0.80 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 2.660702E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.100 | TFLOPs: 19.37 | +31: iteration 3350/ 39672 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 0.80 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 2.642517E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.312 | TFLOPs: 19.38 | +31: iteration 3360/ 39672 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 0.80 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 2.629614E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.828 | TFLOPs: 19.47 | +31: iteration 3370/ 39672 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 0.81 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 2.645747E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.333 | TFLOPs: 19.02 | +31: iteration 3380/ 39672 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 0.81 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 2.624165E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.766 | TFLOPs: 19.10 | +31: iteration 3390/ 39672 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 0.82 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 2.618856E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.593 | TFLOPs: 18.85 | +31: iteration 3400/ 39672 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 0.78 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 2.592452E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.810 | TFLOPs: 19.95 | +31: iteration 3410/ 39672 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 0.80 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 2.652192E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.829 | TFLOPs: 19.35 | +31: iteration 3420/ 39672 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 0.76 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 2.636248E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.202 | TFLOPs: 20.34 | +31: iteration 3430/ 39672 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 0.77 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 2.592439E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.240 | TFLOPs: 20.10 | +31: iteration 3440/ 39672 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 0.82 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 2.564866E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.050 | TFLOPs: 18.94 | +31: iteration 3450/ 39672 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 0.77 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 2.626167E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.405 | TFLOPs: 20.23 | +31: iteration 3460/ 39672 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 0.76 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 2.600050E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.827 | TFLOPs: 20.38 | +31: iteration 3470/ 39672 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 0.74 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 2.628222E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.779 | TFLOPs: 20.98 | +31: iteration 3480/ 39672 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 0.77 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 2.613583E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.783 | TFLOPs: 20.19 | +31: iteration 3490/ 39672 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 0.84 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 2.584783E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.701 | TFLOPs: 18.49 | +31: iteration 3500/ 39672 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 0.84 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 2.584827E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.153 | TFLOPs: 18.34 | +31: iteration 3510/ 39672 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 0.84 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 2.599064E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.461 | TFLOPs: 18.42 | +31: iteration 3520/ 39672 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 0.82 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 2.577830E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.736 | TFLOPs: 18.92 | +31: iteration 3530/ 39672 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 0.76 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 2.603896E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.281 | TFLOPs: 20.28 | +31: iteration 3540/ 39672 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 0.79 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 2.621628E+00 | grad norm: 0.711 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.634 | TFLOPs: 19.58 | +31: iteration 3550/ 39672 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 0.78 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 2.615680E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.340 | TFLOPs: 19.86 | +31: iteration 3560/ 39672 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 0.78 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 2.701292E+00 | grad norm: 1.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.968 | TFLOPs: 19.96 | +31: iteration 3570/ 39672 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 0.76 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 2.670794E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.701 | TFLOPs: 20.25 | +31: iteration 3580/ 39672 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 0.79 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 2.646243E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.792 | TFLOPs: 19.53 | +31: iteration 3590/ 39672 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 0.74 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 2.589527E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.077 | TFLOPs: 21.06 | +31: iteration 3600/ 39672 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 0.83 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 2.598610E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.846 | TFLOPs: 18.62 | +31: iteration 3610/ 39672 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 0.77 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 2.617035E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.539 | TFLOPs: 20.24 | +31: iteration 3620/ 39672 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 0.77 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 2.579275E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.334 | TFLOPs: 20.23 | +31: iteration 3630/ 39672 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 0.77 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 2.609792E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.206 | TFLOPs: 20.22 | +31: iteration 3640/ 39672 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 0.85 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 2.617383E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.917 | TFLOPs: 18.33 | +31: iteration 3650/ 39672 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 0.84 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 2.575227E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.924 | TFLOPs: 18.51 | +31: iteration 3660/ 39672 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 0.74 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 2.579299E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.039 | TFLOPs: 21.06 | +31: iteration 3670/ 39672 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 0.81 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 2.572740E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.080 | TFLOPs: 19.12 | +31: iteration 3680/ 39672 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 0.74 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 2.608050E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.302 | TFLOPs: 20.95 | +31: iteration 3690/ 39672 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 0.73 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 2.604310E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.476 | TFLOPs: 21.14 | +31: iteration 3700/ 39672 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 0.74 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 2.581057E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.942 | TFLOPs: 20.81 | +31: iteration 3710/ 39672 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 0.73 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 2.588957E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.063 | TFLOPs: 21.18 | +31: iteration 3720/ 39672 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 0.73 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 2.603872E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.150 | TFLOPs: 21.12 | +31: iteration 3730/ 39672 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 0.76 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 2.592285E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.732 | TFLOPs: 20.37 | +31: iteration 3740/ 39672 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 0.78 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 2.574016E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.382 | TFLOPs: 19.87 | +31: iteration 3750/ 39672 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 0.86 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 2.602645E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.834 | TFLOPs: 18.02 | +31: iteration 3760/ 39672 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 0.82 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 2.553429E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.122 | TFLOPs: 18.88 | +31: iteration 3770/ 39672 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 0.84 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 2.578833E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.547 | TFLOPs: 18.42 | +31: iteration 3780/ 39672 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 0.79 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 2.574432E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.048 | TFLOPs: 19.48 | +31: iteration 3790/ 39672 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 0.78 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 2.585704E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.571 | TFLOPs: 19.76 | +31: iteration 3800/ 39672 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 0.82 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 2.586026E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.686 | TFLOPs: 18.80 | +31: iteration 3810/ 39672 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 0.75 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 2.573531E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.043 | TFLOPs: 20.57 | +31: iteration 3820/ 39672 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 0.79 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 2.588082E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.296 | TFLOPs: 19.56 | +31: iteration 3830/ 39672 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 0.76 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 2.603305E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.621 | TFLOPs: 20.30 | +31: iteration 3840/ 39672 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 0.78 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 2.570399E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.089 | TFLOPs: 19.97 | +31: iteration 3850/ 39672 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 0.76 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 2.544635E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.430 | TFLOPs: 20.29 | +31: iteration 3860/ 39672 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 0.82 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 2.564199E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.924 | TFLOPs: 18.99 | +31: iteration 3870/ 39672 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 0.75 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 2.534026E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.223 | TFLOPs: 20.76 | +31: iteration 3880/ 39672 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 0.79 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 2.583982E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.920 | TFLOPs: 19.60 | +31: iteration 3890/ 39672 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 0.82 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 2.582204E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.144 | TFLOPs: 18.94 | +31: iteration 3900/ 39672 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 0.78 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 2.546625E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.982 | TFLOPs: 19.90 | +31: iteration 3910/ 39672 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 0.82 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 2.565629E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.650 | TFLOPs: 18.91 | +31: iteration 3920/ 39672 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 0.75 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 2.580601E+00 | grad norm: 0.785 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.180 | TFLOPs: 20.76 | +31: iteration 3930/ 39672 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 0.81 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 2.651842E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.284 | TFLOPs: 19.13 | +31: iteration 3940/ 39672 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 0.74 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 2.563025E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.696 | TFLOPs: 21.03 | +31: iteration 3950/ 39672 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 0.79 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 2.575477E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.190 | TFLOPs: 19.55 | +31: iteration 3960/ 39672 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 0.76 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 2.542656E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.445 | TFLOPs: 20.35 | +31: iteration 3970/ 39672 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 0.76 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 2.596645E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.660 | TFLOPs: 20.37 | +31: iteration 3980/ 39672 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 0.78 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 2.570801E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.253 | TFLOPs: 19.74 | +31: iteration 3990/ 39672 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 0.75 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 2.584673E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.874 | TFLOPs: 20.62 | + 0: [2022-11-30 10:08:17,845] [INFO] [logging.py:68:log_dist] [Rank 0] step=4000, skipped=0, lr=[0.00019628772495253394, 0.00019628772495253394, 0.00019628772495253394], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 4000/ 39672 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 0.75 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 2.543876E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.241 | TFLOPs: 20.64 | + 0: steps: 4000 loss: 2.5077 iter time (s): 0.790 samples/sec: 323.953 +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 4000 | lm loss value: 2.633288E+00 | lm loss PPL: 1.391946E+01 | +31: ------------------------------------------------------------------------------------------ +31: iteration 4010/ 39672 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 0.82 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 2.550515E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.334 | TFLOPs: 18.90 | +31: iteration 4020/ 39672 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 0.72 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 2.581254E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.930 | TFLOPs: 21.59 | +31: iteration 4030/ 39672 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 0.76 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 2.550129E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.058 | TFLOPs: 20.27 | +31: iteration 4040/ 39672 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 0.79 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 2.524270E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.594 | TFLOPs: 19.70 | +31: iteration 4050/ 39672 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 0.78 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 2.533865E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.851 | TFLOPs: 19.89 | +31: iteration 4060/ 39672 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 0.76 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 2.570658E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.784 | TFLOPs: 20.50 | +31: iteration 4070/ 39672 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 0.78 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 2.581301E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.412 | TFLOPs: 19.87 | +31: iteration 4080/ 39672 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 0.75 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 2.549977E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.426 | TFLOPs: 20.72 | +31: iteration 4090/ 39672 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 0.80 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 2.558867E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.053 | TFLOPs: 19.36 | +31: iteration 4100/ 39672 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 0.74 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 2.551007E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.384 | TFLOPs: 20.89 | +31: iteration 4110/ 39672 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 0.80 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 2.516760E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.987 | TFLOPs: 19.42 | +31: iteration 4120/ 39672 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 0.80 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 2.511171E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.019 | TFLOPs: 19.30 | +31: iteration 4130/ 39672 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 0.79 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 2.516972E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.280 | TFLOPs: 19.68 | +31: iteration 4140/ 39672 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 0.75 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 2.532880E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.228 | TFLOPs: 20.70 | +31: iteration 4150/ 39672 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 0.80 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 2.544909E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.280 | TFLOPs: 19.26 | +31: iteration 4160/ 39672 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 0.77 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 2.544084E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.255 | TFLOPs: 20.04 | +31: iteration 4170/ 39672 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 0.83 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 2.518616E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.898 | TFLOPs: 18.69 | +31: iteration 4180/ 39672 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 0.76 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 2.538243E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.667 | TFLOPs: 20.25 | +31: iteration 4190/ 39672 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 0.74 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 2.507385E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.752 | TFLOPs: 20.80 | +31: iteration 4200/ 39672 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 0.78 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 2.541167E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.441 | TFLOPs: 19.93 | +31: iteration 4210/ 39672 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 0.73 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 2.536557E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.767 | TFLOPs: 21.22 | +31: iteration 4220/ 39672 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 0.80 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 2.555351E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.250 | TFLOPs: 19.43 | +31: iteration 4230/ 39672 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 0.78 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 2.534155E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.487 | TFLOPs: 19.81 | +31: iteration 4240/ 39672 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 0.76 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 2.534603E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.183 | TFLOPs: 20.46 | +31: iteration 4250/ 39672 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 0.79 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 2.514294E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.272 | TFLOPs: 19.62 | +31: iteration 4260/ 39672 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 0.74 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 2.539518E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.862 | TFLOPs: 21.04 | +31: iteration 4270/ 39672 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 0.77 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 2.500342E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.398 | TFLOPs: 19.99 | +31: iteration 4280/ 39672 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 0.80 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 2.542884E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.673 | TFLOPs: 19.28 | +31: iteration 4290/ 39672 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 0.79 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 2.524264E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.489 | TFLOPs: 19.57 | +31: iteration 4300/ 39672 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 0.76 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 2.539046E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.273 | TFLOPs: 20.46 | +31: iteration 4310/ 39672 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 0.79 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 2.527693E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.127 | TFLOPs: 19.55 | +31: iteration 4320/ 39672 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 0.76 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 2.523841E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.414 | TFLOPs: 20.41 | +31: iteration 4330/ 39672 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 0.76 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 2.500467E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.577 | TFLOPs: 20.48 | +31: iteration 4340/ 39672 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 0.80 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 2.560726E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.230 | TFLOPs: 19.37 | +31: iteration 4350/ 39672 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 0.80 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 2.531070E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.195 | TFLOPs: 19.43 | +31: iteration 4360/ 39672 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 0.83 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 2.523619E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.872 | TFLOPs: 18.57 | +31: iteration 4370/ 39672 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 0.79 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 2.557109E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.439 | TFLOPs: 19.69 | +31: iteration 4380/ 39672 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 0.79 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 2.521064E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.374 | TFLOPs: 19.50 | +31: iteration 4390/ 39672 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 0.78 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 2.551070E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.271 | TFLOPs: 19.86 | +31: iteration 4400/ 39672 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 0.84 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 2.529983E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.063 | TFLOPs: 18.52 | +31: iteration 4410/ 39672 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 0.80 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 2.507077E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.713 | TFLOPs: 19.40 | +31: iteration 4420/ 39672 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 0.81 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 2.517048E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.373 | TFLOPs: 19.14 | +31: iteration 4430/ 39672 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 0.77 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 2.491954E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.018 | TFLOPs: 20.15 | +31: iteration 4440/ 39672 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 0.75 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 2.527522E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.942 | TFLOPs: 20.63 | +31: iteration 4450/ 39672 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 0.75 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 2.530672E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.599 | TFLOPs: 20.67 | +31: iteration 4460/ 39672 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 0.85 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 2.470706E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.053 | TFLOPs: 18.15 | +31: iteration 4470/ 39672 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 0.85 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 2.509580E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.451 | TFLOPs: 18.30 | +31: iteration 4480/ 39672 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 0.82 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 2.528157E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.591 | TFLOPs: 18.85 | +31: iteration 4490/ 39672 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 0.80 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 2.482819E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.431 | TFLOPs: 19.45 | +31: iteration 4500/ 39672 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 0.76 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 2.514047E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.534 | TFLOPs: 20.42 | +31: iteration 4510/ 39672 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 0.75 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 2.496424E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.197 | TFLOPs: 20.52 | +31: iteration 4520/ 39672 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 0.77 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 2.518221E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.115 | TFLOPs: 20.15 | +31: iteration 4530/ 39672 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 0.77 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 2.542165E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.197 | TFLOPs: 20.16 | +31: iteration 4540/ 39672 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 0.77 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 2.520563E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.971 | TFLOPs: 20.08 | +31: iteration 4550/ 39672 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 0.79 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 2.495441E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.317 | TFLOPs: 19.56 | +31: iteration 4560/ 39672 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 0.79 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 2.510847E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.285 | TFLOPs: 19.68 | +31: iteration 4570/ 39672 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 0.76 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 2.499012E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.231 | TFLOPs: 20.34 | +31: iteration 4580/ 39672 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 0.75 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 2.521926E+00 | grad norm: 0.540 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.579 | TFLOPs: 20.73 | +31: iteration 4590/ 39672 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 0.77 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 2.617262E+00 | grad norm: 0.906 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.814 | TFLOPs: 20.07 | +31: iteration 4600/ 39672 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 0.76 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 2.904634E+00 | grad norm: 2.814 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.332 | TFLOPs: 20.41 | +31: iteration 4610/ 39672 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 0.81 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 2.889826E+00 | grad norm: 2.600 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.697 | TFLOPs: 19.22 | +31: iteration 4620/ 39672 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 0.76 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 2.802634E+00 | grad norm: 1.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.272 | TFLOPs: 20.28 | +31: iteration 4630/ 39672 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 0.78 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 2.719914E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.238 | TFLOPs: 19.80 | +31: iteration 4640/ 39672 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 0.80 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 2.642788E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.492 | TFLOPs: 19.45 | +31: iteration 4650/ 39672 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 0.78 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 2.566479E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.217 | TFLOPs: 19.92 | +31: iteration 4660/ 39672 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 0.76 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 2.548043E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.248 | TFLOPs: 20.28 | +31: iteration 4670/ 39672 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 0.83 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 2.520415E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.740 | TFLOPs: 18.56 | +31: iteration 4680/ 39672 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 0.79 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 2.529613E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.936 | TFLOPs: 19.60 | +31: iteration 4690/ 39672 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 0.72 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 2.548282E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.496 | TFLOPs: 21.51 | +31: iteration 4700/ 39672 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 0.76 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 2.529050E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.988 | TFLOPs: 20.33 | +31: iteration 4710/ 39672 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 0.77 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 2.503726E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.564 | TFLOPs: 20.24 | +31: iteration 4720/ 39672 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 0.76 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 2.521817E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.921 | TFLOPs: 20.32 | +31: iteration 4730/ 39672 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 0.77 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 2.494547E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.008 | TFLOPs: 20.03 | +31: iteration 4740/ 39672 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 0.83 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 2.516681E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.533 | TFLOPs: 18.67 | +31: iteration 4750/ 39672 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 0.83 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 2.508540E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.519 | TFLOPs: 18.66 | +31: iteration 4760/ 39672 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 0.75 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 2.513975E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.486 | TFLOPs: 20.72 | +31: iteration 4770/ 39672 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 0.77 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 2.540583E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.442 | TFLOPs: 20.17 | +31: iteration 4780/ 39672 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 0.77 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 2.494842E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.377 | TFLOPs: 20.23 | +31: iteration 4790/ 39672 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 0.77 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 2.517473E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.242 | TFLOPs: 20.22 | +31: iteration 4800/ 39672 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 0.73 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 2.532445E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.724 | TFLOPs: 21.16 | +31: iteration 4810/ 39672 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 0.73 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 2.514964E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.387 | TFLOPs: 21.14 | +31: iteration 4820/ 39672 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 0.97 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 2.499219E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 264.954 | TFLOPs: 16.03 | +31: iteration 4830/ 39672 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 0.75 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 2.487116E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.479 | TFLOPs: 20.54 | +31: iteration 4840/ 39672 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 0.76 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 2.463767E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.017 | TFLOPs: 20.33 | +31: iteration 4850/ 39672 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 0.81 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 2.499249E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.793 | TFLOPs: 19.04 | +31: iteration 4860/ 39672 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 0.93 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 2.529788E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 273.843 | TFLOPs: 16.57 | +31: iteration 4870/ 39672 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 0.80 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 2.489380E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.542 | TFLOPs: 19.27 | +31: iteration 4880/ 39672 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 0.79 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 2.533626E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.034 | TFLOPs: 19.48 | +31: iteration 4890/ 39672 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 0.85 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 2.541739E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.306 | TFLOPs: 18.23 | +31: iteration 4900/ 39672 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 0.86 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 2.492345E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.026 | TFLOPs: 18.03 | +31: iteration 4910/ 39672 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 0.81 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 2.475246E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.759 | TFLOPs: 19.04 | +31: iteration 4920/ 39672 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 0.83 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 2.517241E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.384 | TFLOPs: 18.66 | +31: iteration 4930/ 39672 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 0.81 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 2.493414E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.645 | TFLOPs: 19.10 | +31: iteration 4940/ 39672 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 0.79 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 2.504113E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.108 | TFLOPs: 19.49 | +31: iteration 4950/ 39672 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 0.78 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 2.523809E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.701 | TFLOPs: 19.89 | +31: iteration 4960/ 39672 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 0.77 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 2.492248E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.159 | TFLOPs: 20.09 | +31: iteration 4970/ 39672 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 0.74 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 2.487013E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.834 | TFLOPs: 20.80 | +31: iteration 4980/ 39672 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 0.80 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 2.500854E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.136 | TFLOPs: 19.43 | +31: iteration 4990/ 39672 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 0.80 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 2.479378E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.639 | TFLOPs: 19.34 | +31: iteration 5000/ 39672 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 0.82 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 2.475186E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.991 | TFLOPs: 19.00 | +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 5000 | lm loss value: 2.520253E+00 | lm loss PPL: 1.243174E+01 | +31: ------------------------------------------------------------------------------------------ +31: iteration 5010/ 39672 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 0.83 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 2.485467E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.069 | TFLOPs: 18.58 | +31: iteration 5020/ 39672 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 0.84 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 2.466754E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.275 | TFLOPs: 18.53 | +31: iteration 5030/ 39672 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 0.83 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 2.479723E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.259 | TFLOPs: 18.71 | +31: iteration 5040/ 39672 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 0.80 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 2.459732E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.754 | TFLOPs: 19.28 | +31: iteration 5050/ 39672 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 0.76 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 2.454614E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.600 | TFLOPs: 20.36 | +31: iteration 5060/ 39672 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 0.78 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 2.458179E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.485 | TFLOPs: 19.87 | +31: iteration 5070/ 39672 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 0.74 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 2.477728E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.216 | TFLOPs: 20.82 | +31: iteration 5080/ 39672 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 0.79 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 2.501203E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.386 | TFLOPs: 19.62 | +31: iteration 5090/ 39672 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 0.78 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 2.481656E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.479 | TFLOPs: 19.93 | +31: iteration 5100/ 39672 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 0.78 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 2.508315E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.809 | TFLOPs: 19.89 | +31: iteration 5110/ 39672 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 0.83 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 2.486010E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.252 | TFLOPs: 18.77 | +31: iteration 5120/ 39672 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 0.78 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 2.494689E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.828 | TFLOPs: 19.77 | +31: iteration 5130/ 39672 | consumed samples: 1313280 | consumed tokens: 2689597440 | elapsed time per iteration (s): 0.73 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 2.491791E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.114 | TFLOPs: 21.18 | +31: iteration 5140/ 39672 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 0.75 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 2.477937E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.365 | TFLOPs: 20.77 | +31: iteration 5150/ 39672 | consumed samples: 1318400 | consumed tokens: 2700083200 | elapsed time per iteration (s): 0.75 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 2.491364E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.909 | TFLOPs: 20.56 | +31: iteration 5160/ 39672 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 0.76 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 2.492126E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.715 | TFLOPs: 20.25 | +31: iteration 5170/ 39672 | consumed samples: 1323520 | consumed tokens: 2710568960 | elapsed time per iteration (s): 0.79 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 2.474740E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.875 | TFLOPs: 19.53 | +31: iteration 5180/ 39672 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 0.74 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 2.485264E+00 | grad norm: 0.518 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.438 | TFLOPs: 20.90 | +31: iteration 5190/ 39672 | consumed samples: 1328640 | consumed tokens: 2721054720 | elapsed time per iteration (s): 0.84 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 2.467282E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.497 | TFLOPs: 18.42 | +31: iteration 5200/ 39672 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 0.77 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 2.481091E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.912 | TFLOPs: 20.14 | +31: iteration 5210/ 39672 | consumed samples: 1333760 | consumed tokens: 2731540480 | elapsed time per iteration (s): 0.77 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 2.458110E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.441 | TFLOPs: 19.99 | +31: iteration 5220/ 39672 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 0.77 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 2.464642E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.423 | TFLOPs: 19.99 | +31: iteration 5230/ 39672 | consumed samples: 1338880 | consumed tokens: 2742026240 | elapsed time per iteration (s): 0.77 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 2.501975E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.327 | TFLOPs: 20.23 | +31: iteration 5240/ 39672 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 0.77 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 2.459733E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.488 | TFLOPs: 20.11 | +31: iteration 5250/ 39672 | consumed samples: 1344000 | consumed tokens: 2752512000 | elapsed time per iteration (s): 0.84 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 2.488954E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.041 | TFLOPs: 18.39 | +31: iteration 5260/ 39672 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 0.80 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 2.498966E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.034 | TFLOPs: 19.24 | +31: iteration 5270/ 39672 | consumed samples: 1349120 | consumed tokens: 2762997760 | elapsed time per iteration (s): 0.80 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 2.438149E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.150 | TFLOPs: 19.43 | +31: iteration 5280/ 39672 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 0.78 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 2.488787E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.999 | TFLOPs: 19.78 | +31: iteration 5290/ 39672 | consumed samples: 1354240 | consumed tokens: 2773483520 | elapsed time per iteration (s): 0.81 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 2.453190E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.081 | TFLOPs: 19.12 | +31: iteration 5300/ 39672 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 0.80 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 2.458907E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.642 | TFLOPs: 19.46 | +31: iteration 5310/ 39672 | consumed samples: 1359360 | consumed tokens: 2783969280 | elapsed time per iteration (s): 0.77 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 2.494486E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.254 | TFLOPs: 20.16 | +31: iteration 5320/ 39672 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 0.82 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 2.465764E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.050 | TFLOPs: 18.88 | +31: iteration 5330/ 39672 | consumed samples: 1364480 | consumed tokens: 2794455040 | elapsed time per iteration (s): 0.81 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 2.471799E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.414 | TFLOPs: 19.20 | +31: iteration 5340/ 39672 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 0.77 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 2.492515E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.424 | TFLOPs: 20.17 | +31: iteration 5350/ 39672 | consumed samples: 1369600 | consumed tokens: 2804940800 | elapsed time per iteration (s): 0.83 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 2.445299E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.147 | TFLOPs: 18.70 | +31: iteration 5360/ 39672 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 0.75 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 2.495334E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.302 | TFLOPs: 20.59 | +31: iteration 5370/ 39672 | consumed samples: 1374720 | consumed tokens: 2815426560 | elapsed time per iteration (s): 0.75 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 2.479818E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.638 | TFLOPs: 20.55 | +31: iteration 5380/ 39672 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 0.82 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 2.438895E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.930 | TFLOPs: 18.87 | +31: iteration 5390/ 39672 | consumed samples: 1379840 | consumed tokens: 2825912320 | elapsed time per iteration (s): 0.81 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 2.474482E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.346 | TFLOPs: 19.20 | +31: iteration 5400/ 39672 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 0.78 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 2.437750E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.369 | TFLOPs: 19.93 | +31: iteration 5410/ 39672 | consumed samples: 1384960 | consumed tokens: 2836398080 | elapsed time per iteration (s): 0.80 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 2.471066E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.213 | TFLOPs: 19.25 | +31: iteration 5420/ 39672 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 0.82 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 2.457968E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.447 | TFLOPs: 18.96 | +31: iteration 5430/ 39672 | consumed samples: 1390080 | consumed tokens: 2846883840 | elapsed time per iteration (s): 0.79 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 2.481283E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.877 | TFLOPs: 19.59 | +31: iteration 5440/ 39672 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 0.79 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 2.464102E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.570 | TFLOPs: 19.51 | +31: iteration 5450/ 39672 | consumed samples: 1395200 | consumed tokens: 2857369600 | elapsed time per iteration (s): 0.86 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 2.467360E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.126 | TFLOPs: 18.04 | +31: iteration 5460/ 39672 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 0.85 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 2.485507E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.276 | TFLOPs: 18.17 | +31: iteration 5470/ 39672 | consumed samples: 1400320 | consumed tokens: 2867855360 | elapsed time per iteration (s): 0.85 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 2.464048E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.064 | TFLOPs: 18.15 | +31: iteration 5480/ 39672 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 0.89 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 2.460804E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 287.890 | TFLOPs: 17.42 | +31: iteration 5490/ 39672 | consumed samples: 1405440 | consumed tokens: 2878341120 | elapsed time per iteration (s): 0.82 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 2.434087E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.528 | TFLOPs: 18.85 | +31: iteration 5500/ 39672 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 0.83 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 2.491623E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.682 | TFLOPs: 18.61 | +31: iteration 5510/ 39672 | consumed samples: 1410560 | consumed tokens: 2888826880 | elapsed time per iteration (s): 0.81 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 2.459441E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.286 | TFLOPs: 19.07 | +31: iteration 5520/ 39672 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 0.81 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 2.489108E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.624 | TFLOPs: 19.15 | +31: iteration 5530/ 39672 | consumed samples: 1415680 | consumed tokens: 2899312640 | elapsed time per iteration (s): 0.83 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 2.457578E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.789 | TFLOPs: 18.74 | +31: iteration 5540/ 39672 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 0.79 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 2.497273E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.985 | TFLOPs: 19.66 | +31: iteration 5550/ 39672 | consumed samples: 1420800 | consumed tokens: 2909798400 | elapsed time per iteration (s): 0.85 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 2.463666E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.863 | TFLOPs: 18.20 | +31: iteration 5560/ 39672 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 0.78 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 2.456889E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.941 | TFLOPs: 19.90 | +31: iteration 5570/ 39672 | consumed samples: 1425920 | consumed tokens: 2920284160 | elapsed time per iteration (s): 0.83 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 2.504575E+00 | grad norm: 14.728 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.401 | TFLOPs: 18.60 | +31: iteration 5580/ 39672 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 0.79 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 2.488984E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.261 | TFLOPs: 19.56 | +31: iteration 5590/ 39672 | consumed samples: 1431040 | consumed tokens: 2930769920 | elapsed time per iteration (s): 0.84 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 2.472685E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.223 | TFLOPs: 18.53 | +31: iteration 5600/ 39672 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 0.78 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 2.452278E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.410 | TFLOPs: 19.87 | +31: iteration 5610/ 39672 | consumed samples: 1436160 | consumed tokens: 2941255680 | elapsed time per iteration (s): 0.79 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 2.501245E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.058 | TFLOPs: 19.54 | +31: iteration 5620/ 39672 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 0.84 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 2.449909E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.386 | TFLOPs: 18.35 | +31: iteration 5630/ 39672 | consumed samples: 1441280 | consumed tokens: 2951741440 | elapsed time per iteration (s): 0.82 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 2.495840E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.292 | TFLOPs: 18.83 | +31: iteration 5640/ 39672 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 0.79 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 2.417732E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.203 | TFLOPs: 19.49 | +31: iteration 5650/ 39672 | consumed samples: 1446400 | consumed tokens: 2962227200 | elapsed time per iteration (s): 0.78 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 2.466424E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.855 | TFLOPs: 19.96 | +31: iteration 5660/ 39672 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 0.78 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 2.450133E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.345 | TFLOPs: 19.86 | +31: iteration 5670/ 39672 | consumed samples: 1451520 | consumed tokens: 2972712960 | elapsed time per iteration (s): 0.73 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 2.481678E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.542 | TFLOPs: 21.21 | +31: iteration 5680/ 39672 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 0.78 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 2.464660E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.249 | TFLOPs: 19.86 | +31: iteration 5690/ 39672 | consumed samples: 1456640 | consumed tokens: 2983198720 | elapsed time per iteration (s): 0.74 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 2.502679E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.096 | TFLOPs: 20.88 | +31: iteration 5700/ 39672 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 0.78 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 2.479009E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.055 | TFLOPs: 19.91 | +31: iteration 5710/ 39672 | consumed samples: 1461760 | consumed tokens: 2993684480 | elapsed time per iteration (s): 0.86 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 2.450927E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.672 | TFLOPs: 18.07 | +31: iteration 5720/ 39672 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 0.77 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 2.433856E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.808 | TFLOPs: 20.19 | +31: iteration 5730/ 39672 | consumed samples: 1466880 | consumed tokens: 3004170240 | elapsed time per iteration (s): 0.78 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 2.477681E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.871 | TFLOPs: 19.96 | +31: iteration 5740/ 39672 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 0.72 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 2.449261E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.614 | TFLOPs: 21.39 | +31: iteration 5750/ 39672 | consumed samples: 1472000 | consumed tokens: 3014656000 | elapsed time per iteration (s): 0.73 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 2.409764E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.569 | TFLOPs: 21.15 | +31: iteration 5760/ 39672 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 0.73 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 2.448725E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.665 | TFLOPs: 21.34 | +31: iteration 5770/ 39672 | consumed samples: 1477120 | consumed tokens: 3025141760 | elapsed time per iteration (s): 0.78 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 2.440396E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.227 | TFLOPs: 19.92 | +31: iteration 5780/ 39672 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 0.75 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 2.442277E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.570 | TFLOPs: 20.54 | +31: iteration 5790/ 39672 | consumed samples: 1482240 | consumed tokens: 3035627520 | elapsed time per iteration (s): 0.79 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 2.451942E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.058 | TFLOPs: 19.54 | +31: iteration 5800/ 39672 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 0.72 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 2.473244E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.146 | TFLOPs: 21.36 | +31: iteration 5810/ 39672 | consumed samples: 1487360 | consumed tokens: 3046113280 | elapsed time per iteration (s): 0.74 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 2.442479E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.838 | TFLOPs: 20.80 | +31: iteration 5820/ 39672 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 0.75 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 2.474461E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.111 | TFLOPs: 20.64 | +31: iteration 5830/ 39672 | consumed samples: 1492480 | consumed tokens: 3056599040 | elapsed time per iteration (s): 0.78 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 2.440588E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.357 | TFLOPs: 19.93 | +31: iteration 5840/ 39672 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 0.77 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 2.456872E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.386 | TFLOPs: 20.23 | +31: iteration 5850/ 39672 | consumed samples: 1497600 | consumed tokens: 3067084800 | elapsed time per iteration (s): 0.79 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 2.463838E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.169 | TFLOPs: 19.55 | +31: iteration 5860/ 39672 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 0.80 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 2.455319E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.903 | TFLOPs: 19.47 | +31: iteration 5870/ 39672 | consumed samples: 1502720 | consumed tokens: 3077570560 | elapsed time per iteration (s): 0.77 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 2.454759E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.195 | TFLOPs: 20.10 | +31: iteration 5880/ 39672 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 0.72 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 2.451006E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.856 | TFLOPs: 21.41 | +31: iteration 5890/ 39672 | consumed samples: 1507840 | consumed tokens: 3088056320 | elapsed time per iteration (s): 0.73 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 2.413034E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.258 | TFLOPs: 21.25 | +31: iteration 5900/ 39672 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 0.72 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 2.425305E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.814 | TFLOPs: 21.59 | +31: iteration 5910/ 39672 | consumed samples: 1512960 | consumed tokens: 3098542080 | elapsed time per iteration (s): 0.79 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 2.441942E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.527 | TFLOPs: 19.69 | +31: iteration 5920/ 39672 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 0.79 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 2.461077E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.246 | TFLOPs: 19.56 | +31: iteration 5930/ 39672 | consumed samples: 1518080 | consumed tokens: 3109027840 | elapsed time per iteration (s): 0.80 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 2.440508E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.347 | TFLOPs: 19.26 | +31: iteration 5940/ 39672 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 1.09 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 2.446579E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 235.188 | TFLOPs: 14.23 | +31: iteration 5950/ 39672 | consumed samples: 1523200 | consumed tokens: 3119513600 | elapsed time per iteration (s): 0.78 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 2.453273E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.944 | TFLOPs: 19.78 | +31: iteration 5960/ 39672 | consumed samples: 1525760 | consumed tokens: 3124756480 | elapsed time per iteration (s): 0.75 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 2.448684E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.621 | TFLOPs: 20.67 | +31: iteration 5970/ 39672 | consumed samples: 1528320 | consumed tokens: 3129999360 | elapsed time per iteration (s): 0.78 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 2.487011E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.353 | TFLOPs: 19.86 | +31: iteration 5980/ 39672 | consumed samples: 1530880 | consumed tokens: 3135242240 | elapsed time per iteration (s): 0.77 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 2.449278E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.439 | TFLOPs: 20.11 | +31: iteration 5990/ 39672 | consumed samples: 1533440 | consumed tokens: 3140485120 | elapsed time per iteration (s): 0.76 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 2.455015E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.927 | TFLOPs: 20.26 | + 0: [2022-11-30 10:34:34,022] [INFO] [logging.py:68:log_dist] [Rank 0] step=6000, skipped=0, lr=[0.0001911109368086188, 0.0001911109368086188, 0.0001911109368086188], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 6000/ 39672 | consumed samples: 1536000 | consumed tokens: 3145728000 | elapsed time per iteration (s): 0.79 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 2.444989E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.996 | TFLOPs: 19.66 | + 0: steps: 6000 loss: 2.4533 iter time (s): 0.784 samples/sec: 326.546 +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 6000 | lm loss value: 2.474239E+00 | lm loss PPL: 1.187267E+01 | +31: ------------------------------------------------------------------------------------------ +31: iteration 6010/ 39672 | consumed samples: 1538560 | consumed tokens: 3150970880 | elapsed time per iteration (s): 0.79 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 2.466965E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.351 | TFLOPs: 19.56 | +31: iteration 6020/ 39672 | consumed samples: 1541120 | consumed tokens: 3156213760 | elapsed time per iteration (s): 0.74 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 2.435799E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.465 | TFLOPs: 20.90 | +31: iteration 6030/ 39672 | consumed samples: 1543680 | consumed tokens: 3161456640 | elapsed time per iteration (s): 0.73 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 2.429394E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.942 | TFLOPs: 21.11 | +31: iteration 6040/ 39672 | consumed samples: 1546240 | consumed tokens: 3166699520 | elapsed time per iteration (s): 0.79 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 2.471492E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.663 | TFLOPs: 19.58 | +31: iteration 6050/ 39672 | consumed samples: 1548800 | consumed tokens: 3171942400 | elapsed time per iteration (s): 0.75 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 2.419421E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.639 | TFLOPs: 20.73 | +31: iteration 6060/ 39672 | consumed samples: 1551360 | consumed tokens: 3177185280 | elapsed time per iteration (s): 0.81 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 2.428710E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.185 | TFLOPs: 19.07 | +31: iteration 6070/ 39672 | consumed samples: 1553920 | consumed tokens: 3182428160 | elapsed time per iteration (s): 0.82 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 2.463257E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.028 | TFLOPs: 18.94 | +31: iteration 6080/ 39672 | consumed samples: 1556480 | consumed tokens: 3187671040 | elapsed time per iteration (s): 0.82 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 2.454809E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.404 | TFLOPs: 18.78 | +31: iteration 6090/ 39672 | consumed samples: 1559040 | consumed tokens: 3192913920 | elapsed time per iteration (s): 0.77 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 2.431834E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.661 | TFLOPs: 20.00 | +31: iteration 6100/ 39672 | consumed samples: 1561600 | consumed tokens: 3198156800 | elapsed time per iteration (s): 0.76 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 2.454778E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.627 | TFLOPs: 20.30 | +31: iteration 6110/ 39672 | consumed samples: 1564160 | consumed tokens: 3203399680 | elapsed time per iteration (s): 0.76 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 2.423591E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.809 | TFLOPs: 20.32 | +31: iteration 6120/ 39672 | consumed samples: 1566720 | consumed tokens: 3208642560 | elapsed time per iteration (s): 0.78 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 2.405933E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.200 | TFLOPs: 19.98 | +31: iteration 6130/ 39672 | consumed samples: 1569280 | consumed tokens: 3213885440 | elapsed time per iteration (s): 0.76 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 2.440135E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.208 | TFLOPs: 20.40 | +31: iteration 6140/ 39672 | consumed samples: 1571840 | consumed tokens: 3219128320 | elapsed time per iteration (s): 0.73 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 2.424526E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.776 | TFLOPs: 21.34 | +31: iteration 6150/ 39672 | consumed samples: 1574400 | consumed tokens: 3224371200 | elapsed time per iteration (s): 0.76 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 2.427213E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.526 | TFLOPs: 20.36 | +31: iteration 6160/ 39672 | consumed samples: 1576960 | consumed tokens: 3229614080 | elapsed time per iteration (s): 0.75 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 2.418791E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.737 | TFLOPs: 20.67 | +31: iteration 6170/ 39672 | consumed samples: 1579520 | consumed tokens: 3234856960 | elapsed time per iteration (s): 0.79 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 2.426737E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.442 | TFLOPs: 19.57 | +31: iteration 6180/ 39672 | consumed samples: 1582080 | consumed tokens: 3240099840 | elapsed time per iteration (s): 0.80 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 2.416065E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.714 | TFLOPs: 19.40 | +31: iteration 6190/ 39672 | consumed samples: 1584640 | consumed tokens: 3245342720 | elapsed time per iteration (s): 0.79 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 2.447560E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.940 | TFLOPs: 19.60 | +31: iteration 6200/ 39672 | consumed samples: 1587200 | consumed tokens: 3250585600 | elapsed time per iteration (s): 0.80 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 2.434588E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.200 | TFLOPs: 19.31 | +31: iteration 6210/ 39672 | consumed samples: 1589760 | consumed tokens: 3255828480 | elapsed time per iteration (s): 0.81 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 2.467896E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.439 | TFLOPs: 19.20 | +31: iteration 6220/ 39672 | consumed samples: 1592320 | consumed tokens: 3261071360 | elapsed time per iteration (s): 0.81 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 2.442659E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.717 | TFLOPs: 19.04 | +31: iteration 6230/ 39672 | consumed samples: 1594880 | consumed tokens: 3266314240 | elapsed time per iteration (s): 0.81 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 2.460376E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.139 | TFLOPs: 19.00 | +31: iteration 6240/ 39672 | consumed samples: 1597440 | consumed tokens: 3271557120 | elapsed time per iteration (s): 0.85 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 2.456300E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.024 | TFLOPs: 18.15 | +31: iteration 6250/ 39672 | consumed samples: 1600000 | consumed tokens: 3276800000 | elapsed time per iteration (s): 0.84 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 2.416078E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.969 | TFLOPs: 18.51 | +31: iteration 6260/ 39672 | consumed samples: 1602560 | consumed tokens: 3282042880 | elapsed time per iteration (s): 0.84 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 2.452030E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.494 | TFLOPs: 18.54 | +31: iteration 6270/ 39672 | consumed samples: 1605120 | consumed tokens: 3287285760 | elapsed time per iteration (s): 0.83 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 2.422787E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.217 | TFLOPs: 18.65 | +31: iteration 6280/ 39672 | consumed samples: 1607680 | consumed tokens: 3292528640 | elapsed time per iteration (s): 0.84 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 2.418393E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.498 | TFLOPs: 18.42 | +31: iteration 6290/ 39672 | consumed samples: 1610240 | consumed tokens: 3297771520 | elapsed time per iteration (s): 0.83 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 2.413422E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.026 | TFLOPs: 18.76 | +31: iteration 6300/ 39672 | consumed samples: 1612800 | consumed tokens: 3303014400 | elapsed time per iteration (s): 0.82 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 2.423144E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.438 | TFLOPs: 18.84 | +31: iteration 6310/ 39672 | consumed samples: 1615360 | consumed tokens: 3308257280 | elapsed time per iteration (s): 0.81 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 2.409357E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.744 | TFLOPs: 19.04 | +31: iteration 6320/ 39672 | consumed samples: 1617920 | consumed tokens: 3313500160 | elapsed time per iteration (s): 0.79 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 2.431944E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.629 | TFLOPs: 19.58 | +31: iteration 6330/ 39672 | consumed samples: 1620480 | consumed tokens: 3318743040 | elapsed time per iteration (s): 0.83 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 2.458788E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.322 | TFLOPs: 18.71 | +31: iteration 6340/ 39672 | consumed samples: 1623040 | consumed tokens: 3323985920 | elapsed time per iteration (s): 0.82 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 2.390368E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.170 | TFLOPs: 18.89 | +31: iteration 6350/ 39672 | consumed samples: 1625600 | consumed tokens: 3329228800 | elapsed time per iteration (s): 0.83 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 2.426738E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.153 | TFLOPs: 18.58 | +31: iteration 6360/ 39672 | consumed samples: 1628160 | consumed tokens: 3334471680 | elapsed time per iteration (s): 0.82 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 2.424139E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.433 | TFLOPs: 18.84 | +31: iteration 6370/ 39672 | consumed samples: 1630720 | consumed tokens: 3339714560 | elapsed time per iteration (s): 0.85 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 2.442101E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.457 | TFLOPs: 18.24 | +31: iteration 6380/ 39672 | consumed samples: 1633280 | consumed tokens: 3344957440 | elapsed time per iteration (s): 0.89 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 2.408912E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 286.952 | TFLOPs: 17.36 | +31: iteration 6390/ 39672 | consumed samples: 1635840 | consumed tokens: 3350200320 | elapsed time per iteration (s): 0.80 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 2.419769E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.621 | TFLOPs: 19.34 | +31: iteration 6400/ 39672 | consumed samples: 1638400 | consumed tokens: 3355443200 | elapsed time per iteration (s): 0.85 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 2.420471E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.485 | TFLOPs: 18.30 | +31: iteration 6410/ 39672 | consumed samples: 1640960 | consumed tokens: 3360686080 | elapsed time per iteration (s): 0.85 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 2.440938E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.526 | TFLOPs: 18.18 | +31: iteration 6420/ 39672 | consumed samples: 1643520 | consumed tokens: 3365928960 | elapsed time per iteration (s): 0.82 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 2.400694E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.912 | TFLOPs: 18.99 | +31: iteration 6430/ 39672 | consumed samples: 1646080 | consumed tokens: 3371171840 | elapsed time per iteration (s): 0.81 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 2.421886E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.643 | TFLOPs: 19.04 | +31: iteration 6440/ 39672 | consumed samples: 1648640 | consumed tokens: 3376414720 | elapsed time per iteration (s): 0.78 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 2.423746E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.998 | TFLOPs: 19.90 | +31: iteration 6450/ 39672 | consumed samples: 1651200 | consumed tokens: 3381657600 | elapsed time per iteration (s): 0.81 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 2.418679E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.867 | TFLOPs: 19.11 | +31: iteration 6460/ 39672 | consumed samples: 1653760 | consumed tokens: 3386900480 | elapsed time per iteration (s): 0.84 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 2.384772E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.110 | TFLOPs: 18.46 | +31: iteration 6470/ 39672 | consumed samples: 1656320 | consumed tokens: 3392143360 | elapsed time per iteration (s): 0.82 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 2.402116E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.752 | TFLOPs: 18.86 | +31: iteration 6480/ 39672 | consumed samples: 1658880 | consumed tokens: 3397386240 | elapsed time per iteration (s): 0.80 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 2.429400E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.608 | TFLOPs: 19.46 | +31: iteration 6490/ 39672 | consumed samples: 1661440 | consumed tokens: 3402629120 | elapsed time per iteration (s): 0.78 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 2.411092E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.370 | TFLOPs: 19.93 | +31: iteration 6500/ 39672 | consumed samples: 1664000 | consumed tokens: 3407872000 | elapsed time per iteration (s): 0.78 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 2.390114E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.411 | TFLOPs: 19.87 | +31: iteration 6510/ 39672 | consumed samples: 1666560 | consumed tokens: 3413114880 | elapsed time per iteration (s): 0.80 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 2.419033E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.552 | TFLOPs: 19.45 | +31: iteration 6520/ 39672 | consumed samples: 1669120 | consumed tokens: 3418357760 | elapsed time per iteration (s): 0.80 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 2.431988E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.942 | TFLOPs: 19.42 | +31: iteration 6530/ 39672 | consumed samples: 1671680 | consumed tokens: 3423600640 | elapsed time per iteration (s): 0.78 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 2.398399E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.146 | TFLOPs: 19.91 | +31: iteration 6540/ 39672 | consumed samples: 1674240 | consumed tokens: 3428843520 | elapsed time per iteration (s): 0.82 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 2.403884E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.081 | TFLOPs: 18.94 | +31: iteration 6550/ 39672 | consumed samples: 1676800 | consumed tokens: 3434086400 | elapsed time per iteration (s): 0.79 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 2.434643E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.879 | TFLOPs: 19.53 | +31: iteration 6560/ 39672 | consumed samples: 1679360 | consumed tokens: 3439329280 | elapsed time per iteration (s): 0.82 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 2.417955E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.655 | TFLOPs: 18.85 | +31: iteration 6570/ 39672 | consumed samples: 1681920 | consumed tokens: 3444572160 | elapsed time per iteration (s): 0.81 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 2.420003E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.626 | TFLOPs: 19.09 | +31: iteration 6580/ 39672 | consumed samples: 1684480 | consumed tokens: 3449815040 | elapsed time per iteration (s): 0.79 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 2.426486E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.421 | TFLOPs: 19.51 | +31: iteration 6590/ 39672 | consumed samples: 1687040 | consumed tokens: 3455057920 | elapsed time per iteration (s): 0.91 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 2.413440E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 281.375 | TFLOPs: 17.02 | +31: iteration 6600/ 39672 | consumed samples: 1689600 | consumed tokens: 3460300800 | elapsed time per iteration (s): 0.86 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 2.416477E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.672 | TFLOPs: 17.95 | +31: iteration 6610/ 39672 | consumed samples: 1692160 | consumed tokens: 3465543680 | elapsed time per iteration (s): 0.86 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 2.418100E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.150 | TFLOPs: 18.04 | +31: iteration 6620/ 39672 | consumed samples: 1694720 | consumed tokens: 3470786560 | elapsed time per iteration (s): 0.88 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 2.612293E+00 | grad norm: 9.464 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 290.445 | TFLOPs: 17.57 | +31: iteration 6630/ 39672 | consumed samples: 1697280 | consumed tokens: 3476029440 | elapsed time per iteration (s): 0.86 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 2.710945E+00 | grad norm: 1.774 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.886 | TFLOPs: 17.96 | +31: iteration 6640/ 39672 | consumed samples: 1699840 | consumed tokens: 3481272320 | elapsed time per iteration (s): 0.86 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 2.600925E+00 | grad norm: 1.093 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.967 | TFLOPs: 17.97 | +31: iteration 6650/ 39672 | consumed samples: 1702400 | consumed tokens: 3486515200 | elapsed time per iteration (s): 0.82 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 2.494736E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.897 | TFLOPs: 18.93 | +31: iteration 6660/ 39672 | consumed samples: 1704960 | consumed tokens: 3491758080 | elapsed time per iteration (s): 0.80 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 2.503149E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.994 | TFLOPs: 19.48 | +31: iteration 6670/ 39672 | consumed samples: 1707520 | consumed tokens: 3497000960 | elapsed time per iteration (s): 0.80 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 2.451615E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.972 | TFLOPs: 19.42 | +31: iteration 6680/ 39672 | consumed samples: 1710080 | consumed tokens: 3502243840 | elapsed time per iteration (s): 0.83 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 2.445405E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.061 | TFLOPs: 18.76 | +31: iteration 6690/ 39672 | consumed samples: 1712640 | consumed tokens: 3507486720 | elapsed time per iteration (s): 0.82 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 2.448207E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.521 | TFLOPs: 18.85 | +31: iteration 6700/ 39672 | consumed samples: 1715200 | consumed tokens: 3512729600 | elapsed time per iteration (s): 0.81 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 2.448909E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.579 | TFLOPs: 19.09 | +31: iteration 6710/ 39672 | consumed samples: 1717760 | consumed tokens: 3517972480 | elapsed time per iteration (s): 0.83 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 2.455861E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.076 | TFLOPs: 18.64 | +31: iteration 6720/ 39672 | consumed samples: 1720320 | consumed tokens: 3523215360 | elapsed time per iteration (s): 0.80 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 2.409052E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.106 | TFLOPs: 19.24 | +31: iteration 6730/ 39672 | consumed samples: 1722880 | consumed tokens: 3528458240 | elapsed time per iteration (s): 0.75 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 2.451268E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.017 | TFLOPs: 20.75 | +31: iteration 6740/ 39672 | consumed samples: 1725440 | consumed tokens: 3533701120 | elapsed time per iteration (s): 0.77 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 2.426567E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.070 | TFLOPs: 20.03 | +31: iteration 6750/ 39672 | consumed samples: 1728000 | consumed tokens: 3538944000 | elapsed time per iteration (s): 0.71 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 2.400471E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 360.783 | TFLOPs: 21.83 | +31: iteration 6760/ 39672 | consumed samples: 1730560 | consumed tokens: 3544186880 | elapsed time per iteration (s): 0.79 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 2.419731E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.881 | TFLOPs: 19.53 | +31: iteration 6770/ 39672 | consumed samples: 1733120 | consumed tokens: 3549429760 | elapsed time per iteration (s): 0.77 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 2.381870E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.703 | TFLOPs: 20.19 | +31: iteration 6780/ 39672 | consumed samples: 1735680 | consumed tokens: 3554672640 | elapsed time per iteration (s): 0.73 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 2.394782E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.241 | TFLOPs: 21.25 | +31: iteration 6790/ 39672 | consumed samples: 1738240 | consumed tokens: 3559915520 | elapsed time per iteration (s): 0.74 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 2.414793E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.874 | TFLOPs: 20.80 | +31: iteration 6800/ 39672 | consumed samples: 1740800 | consumed tokens: 3565158400 | elapsed time per iteration (s): 0.83 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 2.461806E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.506 | TFLOPs: 18.66 | +31: iteration 6810/ 39672 | consumed samples: 1743360 | consumed tokens: 3570401280 | elapsed time per iteration (s): 0.82 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 2.406091E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.216 | TFLOPs: 18.89 | +31: iteration 6820/ 39672 | consumed samples: 1745920 | consumed tokens: 3575644160 | elapsed time per iteration (s): 0.79 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 2.408632E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.374 | TFLOPs: 19.68 | +31: iteration 6830/ 39672 | consumed samples: 1748480 | consumed tokens: 3580887040 | elapsed time per iteration (s): 0.81 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 2.478870E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.685 | TFLOPs: 19.16 | +31: iteration 6840/ 39672 | consumed samples: 1751040 | consumed tokens: 3586129920 | elapsed time per iteration (s): 0.77 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 2.431538E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.778 | TFLOPs: 20.01 | +31: iteration 6850/ 39672 | consumed samples: 1753600 | consumed tokens: 3591372800 | elapsed time per iteration (s): 0.82 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 2.417183E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.302 | TFLOPs: 18.95 | +31: iteration 6860/ 39672 | consumed samples: 1756160 | consumed tokens: 3596615680 | elapsed time per iteration (s): 0.76 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 2.397081E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.718 | TFLOPs: 20.37 | +31: iteration 6870/ 39672 | consumed samples: 1758720 | consumed tokens: 3601858560 | elapsed time per iteration (s): 0.84 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 2.443657E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.862 | TFLOPs: 18.50 | +31: iteration 6880/ 39672 | consumed samples: 1761280 | consumed tokens: 3607101440 | elapsed time per iteration (s): 0.78 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 2.430387E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.943 | TFLOPs: 19.84 | +31: iteration 6890/ 39672 | consumed samples: 1763840 | consumed tokens: 3612344320 | elapsed time per iteration (s): 0.74 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 2.365102E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.630 | TFLOPs: 20.79 | +31: iteration 6900/ 39672 | consumed samples: 1766400 | consumed tokens: 3617587200 | elapsed time per iteration (s): 0.78 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 2.372612E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.107 | TFLOPs: 19.79 | +31: iteration 6910/ 39672 | consumed samples: 1768960 | consumed tokens: 3622830080 | elapsed time per iteration (s): 0.78 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 2.405907E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.209 | TFLOPs: 19.92 | +31: iteration 6920/ 39672 | consumed samples: 1771520 | consumed tokens: 3628072960 | elapsed time per iteration (s): 0.74 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 2.402424E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.546 | TFLOPs: 21.03 | +31: iteration 6930/ 39672 | consumed samples: 1774080 | consumed tokens: 3633315840 | elapsed time per iteration (s): 0.75 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 2.396766E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.557 | TFLOPs: 20.66 | +31: iteration 6940/ 39672 | consumed samples: 1776640 | consumed tokens: 3638558720 | elapsed time per iteration (s): 0.75 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 2.415307E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.598 | TFLOPs: 20.79 | +31: iteration 6950/ 39672 | consumed samples: 1779200 | consumed tokens: 3643801600 | elapsed time per iteration (s): 0.78 | learning rate: 1.879E-04 | global batch size: 256 | lm loss: 2.390825E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.764 | TFLOPs: 19.89 | +31: iteration 6960/ 39672 | consumed samples: 1781760 | consumed tokens: 3649044480 | elapsed time per iteration (s): 0.84 | learning rate: 1.879E-04 | global batch size: 256 | lm loss: 2.431711E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.586 | TFLOPs: 18.55 | +31: iteration 6970/ 39672 | consumed samples: 1784320 | consumed tokens: 3654287360 | elapsed time per iteration (s): 0.83 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 2.394072E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.367 | TFLOPs: 18.72 | +31: iteration 6980/ 39672 | consumed samples: 1786880 | consumed tokens: 3659530240 | elapsed time per iteration (s): 0.87 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 2.372938E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 294.513 | TFLOPs: 17.82 | +31: iteration 6990/ 39672 | consumed samples: 1789440 | consumed tokens: 3664773120 | elapsed time per iteration (s): 0.83 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 2.425834E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.270 | TFLOPs: 18.59 | +31: iteration 7000/ 39672 | consumed samples: 1792000 | consumed tokens: 3670016000 | elapsed time per iteration (s): 0.84 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 2.411184E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.000 | TFLOPs: 18.51 | +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 7000 | lm loss value: 2.371321E+00 | lm loss PPL: 1.071153E+01 | +31: ------------------------------------------------------------------------------------------ +31: iteration 7010/ 39672 | consumed samples: 1794560 | consumed tokens: 3675258880 | elapsed time per iteration (s): 0.86 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 2.388238E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.779 | TFLOPs: 17.95 | +31: iteration 7020/ 39672 | consumed samples: 1797120 | consumed tokens: 3680501760 | elapsed time per iteration (s): 0.83 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 2.437488E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.215 | TFLOPs: 18.59 | +31: iteration 7030/ 39672 | consumed samples: 1799680 | consumed tokens: 3685744640 | elapsed time per iteration (s): 0.80 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 2.380327E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.754 | TFLOPs: 19.28 | +31: iteration 7040/ 39672 | consumed samples: 1802240 | consumed tokens: 3690987520 | elapsed time per iteration (s): 0.83 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 2.417395E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.284 | TFLOPs: 18.65 | +31: iteration 7050/ 39672 | consumed samples: 1804800 | consumed tokens: 3696230400 | elapsed time per iteration (s): 0.77 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 2.416633E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.892 | TFLOPs: 20.14 | +31: iteration 7060/ 39672 | consumed samples: 1807360 | consumed tokens: 3701473280 | elapsed time per iteration (s): 0.75 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 2.388244E+00 | grad norm: 0.737 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.921 | TFLOPs: 20.62 | +31: iteration 7070/ 39672 | consumed samples: 1809920 | consumed tokens: 3706716160 | elapsed time per iteration (s): 0.74 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 2.423953E+00 | grad norm: 1.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.277 | TFLOPs: 20.95 | +31: iteration 7080/ 39672 | consumed samples: 1812480 | consumed tokens: 3711959040 | elapsed time per iteration (s): 0.77 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 2.613749E+00 | grad norm: 1.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.892 | TFLOPs: 20.02 | +31: iteration 7090/ 39672 | consumed samples: 1815040 | consumed tokens: 3717201920 | elapsed time per iteration (s): 0.81 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 2.498593E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.925 | TFLOPs: 19.11 | +31: iteration 7100/ 39672 | consumed samples: 1817600 | consumed tokens: 3722444800 | elapsed time per iteration (s): 0.73 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 2.417842E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.544 | TFLOPs: 21.09 | +31: iteration 7110/ 39672 | consumed samples: 1820160 | consumed tokens: 3727687680 | elapsed time per iteration (s): 0.85 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 2.458012E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.424 | TFLOPs: 18.11 | +31: iteration 7120/ 39672 | consumed samples: 1822720 | consumed tokens: 3732930560 | elapsed time per iteration (s): 0.81 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 2.437020E+00 | grad norm: 0.583 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.009 | TFLOPs: 19.06 | +31: iteration 7130/ 39672 | consumed samples: 1825280 | consumed tokens: 3738173440 | elapsed time per iteration (s): 0.75 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 2.452937E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.870 | TFLOPs: 20.56 | +31: iteration 7140/ 39672 | consumed samples: 1827840 | consumed tokens: 3743416320 | elapsed time per iteration (s): 0.74 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 2.414571E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.559 | TFLOPs: 21.03 | +31: iteration 7150/ 39672 | consumed samples: 1830400 | consumed tokens: 3748659200 | elapsed time per iteration (s): 0.75 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 2.415451E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.367 | TFLOPs: 20.53 | +31: iteration 7160/ 39672 | consumed samples: 1832960 | consumed tokens: 3753902080 | elapsed time per iteration (s): 0.72 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 2.437201E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.854 | TFLOPs: 21.59 | +31: iteration 7170/ 39672 | consumed samples: 1835520 | consumed tokens: 3759144960 | elapsed time per iteration (s): 0.74 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 2.434039E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.230 | TFLOPs: 21.01 | +31: iteration 7180/ 39672 | consumed samples: 1838080 | consumed tokens: 3764387840 | elapsed time per iteration (s): 0.76 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 2.413790E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.266 | TFLOPs: 20.28 | +31: iteration 7190/ 39672 | consumed samples: 1840640 | consumed tokens: 3769630720 | elapsed time per iteration (s): 0.77 | learning rate: 1.870E-04 | global batch size: 256 | lm loss: 2.384672E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.497 | TFLOPs: 20.24 | +31: iteration 7200/ 39672 | consumed samples: 1843200 | consumed tokens: 3774873600 | elapsed time per iteration (s): 0.74 | learning rate: 1.870E-04 | global batch size: 256 | lm loss: 2.392405E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.044 | TFLOPs: 20.81 | +31: iteration 7210/ 39672 | consumed samples: 1845760 | consumed tokens: 3780116480 | elapsed time per iteration (s): 0.75 | learning rate: 1.870E-04 | global batch size: 256 | lm loss: 2.403006E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.438 | TFLOPs: 20.60 | +31: iteration 7220/ 39672 | consumed samples: 1848320 | consumed tokens: 3785359360 | elapsed time per iteration (s): 0.74 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 2.400007E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.793 | TFLOPs: 20.92 | +31: iteration 7230/ 39672 | consumed samples: 1850880 | consumed tokens: 3790602240 | elapsed time per iteration (s): 0.76 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 2.409416E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.065 | TFLOPs: 20.39 | +31: iteration 7240/ 39672 | consumed samples: 1853440 | consumed tokens: 3795845120 | elapsed time per iteration (s): 0.72 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 2.418525E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.123 | TFLOPs: 21.54 | +31: iteration 7250/ 39672 | consumed samples: 1856000 | consumed tokens: 3801088000 | elapsed time per iteration (s): 0.74 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 2.429771E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.032 | TFLOPs: 20.81 | +31: iteration 7260/ 39672 | consumed samples: 1858560 | consumed tokens: 3806330880 | elapsed time per iteration (s): 0.76 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 2.378350E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.802 | TFLOPs: 20.38 | +31: iteration 7270/ 39672 | consumed samples: 1861120 | consumed tokens: 3811573760 | elapsed time per iteration (s): 0.74 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 2.417116E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.515 | TFLOPs: 20.96 | +31: iteration 7280/ 39672 | consumed samples: 1863680 | consumed tokens: 3816816640 | elapsed time per iteration (s): 0.71 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 2.418747E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.556 | TFLOPs: 21.75 | +31: iteration 7290/ 39672 | consumed samples: 1866240 | consumed tokens: 3822059520 | elapsed time per iteration (s): 0.76 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 2.408772E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.688 | TFLOPs: 20.49 | +31: iteration 7300/ 39672 | consumed samples: 1868800 | consumed tokens: 3827302400 | elapsed time per iteration (s): 0.76 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 2.415351E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.171 | TFLOPs: 20.46 | +31: iteration 7310/ 39672 | consumed samples: 1871360 | consumed tokens: 3832545280 | elapsed time per iteration (s): 0.73 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 2.404067E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.030 | TFLOPs: 21.36 | +31: iteration 7320/ 39672 | consumed samples: 1873920 | consumed tokens: 3837788160 | elapsed time per iteration (s): 0.77 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 2.388220E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.196 | TFLOPs: 20.04 | +31: iteration 7330/ 39672 | consumed samples: 1876480 | consumed tokens: 3843031040 | elapsed time per iteration (s): 0.75 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 2.402212E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.164 | TFLOPs: 20.76 | +31: iteration 7340/ 39672 | consumed samples: 1879040 | consumed tokens: 3848273920 | elapsed time per iteration (s): 0.77 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 2.372615E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.609 | TFLOPs: 20.06 | +31: iteration 7350/ 39672 | consumed samples: 1881600 | consumed tokens: 3853516800 | elapsed time per iteration (s): 0.77 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 2.392940E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.942 | TFLOPs: 20.20 | +31: iteration 7360/ 39672 | consumed samples: 1884160 | consumed tokens: 3858759680 | elapsed time per iteration (s): 0.73 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 2.407252E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.500 | TFLOPs: 21.26 | +31: iteration 7370/ 39672 | consumed samples: 1886720 | consumed tokens: 3864002560 | elapsed time per iteration (s): 0.84 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 2.389737E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.788 | TFLOPs: 18.44 | +31: iteration 7380/ 39672 | consumed samples: 1889280 | consumed tokens: 3869245440 | elapsed time per iteration (s): 0.74 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 2.393487E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.095 | TFLOPs: 20.82 | +31: iteration 7390/ 39672 | consumed samples: 1891840 | consumed tokens: 3874488320 | elapsed time per iteration (s): 0.83 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 2.362848E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.665 | TFLOPs: 18.73 | +31: iteration 7400/ 39672 | consumed samples: 1894400 | consumed tokens: 3879731200 | elapsed time per iteration (s): 0.73 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 2.401618E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.819 | TFLOPs: 21.10 | +31: iteration 7410/ 39672 | consumed samples: 1896960 | consumed tokens: 3884974080 | elapsed time per iteration (s): 0.83 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 2.409397E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.906 | TFLOPs: 18.75 | +31: iteration 7420/ 39672 | consumed samples: 1899520 | consumed tokens: 3890216960 | elapsed time per iteration (s): 0.79 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 2.362926E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.858 | TFLOPs: 19.53 | +31: iteration 7430/ 39672 | consumed samples: 1902080 | consumed tokens: 3895459840 | elapsed time per iteration (s): 0.75 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 2.391376E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.417 | TFLOPs: 20.53 | +31: iteration 7440/ 39672 | consumed samples: 1904640 | consumed tokens: 3900702720 | elapsed time per iteration (s): 0.82 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 2.342388E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.548 | TFLOPs: 18.85 | +31: iteration 7450/ 39672 | consumed samples: 1907200 | consumed tokens: 3905945600 | elapsed time per iteration (s): 0.74 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 2.388781E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.309 | TFLOPs: 20.83 | +31: iteration 7460/ 39672 | consumed samples: 1909760 | consumed tokens: 3911188480 | elapsed time per iteration (s): 0.77 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 2.400250E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.834 | TFLOPs: 20.08 | +31: iteration 7470/ 39672 | consumed samples: 1912320 | consumed tokens: 3916431360 | elapsed time per iteration (s): 0.80 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 2.372634E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.822 | TFLOPs: 19.47 | +31: iteration 7480/ 39672 | consumed samples: 1914880 | consumed tokens: 3921674240 | elapsed time per iteration (s): 0.75 | learning rate: 1.859E-04 | global batch size: 256 | lm loss: 2.369344E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.574 | TFLOPs: 20.60 | +31: iteration 7490/ 39672 | consumed samples: 1917440 | consumed tokens: 3926917120 | elapsed time per iteration (s): 0.77 | learning rate: 1.859E-04 | global batch size: 256 | lm loss: 2.399230E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.849 | TFLOPs: 20.14 | +31: iteration 7500/ 39672 | consumed samples: 1920000 | consumed tokens: 3932160000 | elapsed time per iteration (s): 0.75 | learning rate: 1.859E-04 | global batch size: 256 | lm loss: 2.361949E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.074 | TFLOPs: 20.63 | +31: iteration 7510/ 39672 | consumed samples: 1922560 | consumed tokens: 3937402880 | elapsed time per iteration (s): 0.78 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 2.369437E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.247 | TFLOPs: 19.74 | +31: iteration 7520/ 39672 | consumed samples: 1925120 | consumed tokens: 3942645760 | elapsed time per iteration (s): 0.71 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 2.411574E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 360.418 | TFLOPs: 21.80 | +31: iteration 7530/ 39672 | consumed samples: 1927680 | consumed tokens: 3947888640 | elapsed time per iteration (s): 0.77 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 2.412524E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.395 | TFLOPs: 20.23 | +31: iteration 7540/ 39672 | consumed samples: 1930240 | consumed tokens: 3953131520 | elapsed time per iteration (s): 0.76 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 2.394713E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.989 | TFLOPs: 20.39 | +31: iteration 7550/ 39672 | consumed samples: 1932800 | consumed tokens: 3958374400 | elapsed time per iteration (s): 0.75 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 2.370593E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.168 | TFLOPs: 20.64 | +31: iteration 7560/ 39672 | consumed samples: 1935360 | consumed tokens: 3963617280 | elapsed time per iteration (s): 0.76 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 2.373408E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.634 | TFLOPs: 20.37 | +31: iteration 7570/ 39672 | consumed samples: 1937920 | consumed tokens: 3968860160 | elapsed time per iteration (s): 0.81 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 2.381986E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.115 | TFLOPs: 19.06 | +31: iteration 7580/ 39672 | consumed samples: 1940480 | consumed tokens: 3974103040 | elapsed time per iteration (s): 0.77 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 2.408358E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.187 | TFLOPs: 20.22 | +31: iteration 7590/ 39672 | consumed samples: 1943040 | consumed tokens: 3979345920 | elapsed time per iteration (s): 0.77 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 2.411914E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.171 | TFLOPs: 20.22 | +31: iteration 7600/ 39672 | consumed samples: 1945600 | consumed tokens: 3984588800 | elapsed time per iteration (s): 0.82 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 2.378177E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.221 | TFLOPs: 18.89 | +31: iteration 7610/ 39672 | consumed samples: 1948160 | consumed tokens: 3989831680 | elapsed time per iteration (s): 0.85 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 2.424384E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.827 | TFLOPs: 18.26 | +31: iteration 7620/ 39672 | consumed samples: 1950720 | consumed tokens: 3995074560 | elapsed time per iteration (s): 0.78 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 2.347099E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.544 | TFLOPs: 19.88 | +31: iteration 7630/ 39672 | consumed samples: 1953280 | consumed tokens: 4000317440 | elapsed time per iteration (s): 0.80 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 2.369359E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.477 | TFLOPs: 19.45 | +31: iteration 7640/ 39672 | consumed samples: 1955840 | consumed tokens: 4005560320 | elapsed time per iteration (s): 0.78 | learning rate: 1.853E-04 | global batch size: 256 | lm loss: 2.396994E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.284 | TFLOPs: 19.86 | +31: iteration 7650/ 39672 | consumed samples: 1958400 | consumed tokens: 4010803200 | elapsed time per iteration (s): 0.74 | learning rate: 1.853E-04 | global batch size: 256 | lm loss: 2.394609E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.924 | TFLOPs: 20.99 | +31: iteration 7660/ 39672 | consumed samples: 1960960 | consumed tokens: 4016046080 | elapsed time per iteration (s): 0.78 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 2.345477E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.868 | TFLOPs: 19.96 | +31: iteration 7670/ 39672 | consumed samples: 1963520 | consumed tokens: 4021288960 | elapsed time per iteration (s): 0.75 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 2.382186E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.950 | TFLOPs: 20.57 | +31: iteration 7680/ 39672 | consumed samples: 1966080 | consumed tokens: 4026531840 | elapsed time per iteration (s): 0.75 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 2.363818E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.138 | TFLOPs: 20.64 | +31: iteration 7690/ 39672 | consumed samples: 1968640 | consumed tokens: 4031774720 | elapsed time per iteration (s): 0.77 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 2.395938E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.400 | TFLOPs: 20.05 | +31: iteration 7700/ 39672 | consumed samples: 1971200 | consumed tokens: 4037017600 | elapsed time per iteration (s): 0.84 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 2.374462E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.015 | TFLOPs: 18.45 | +31: iteration 7710/ 39672 | consumed samples: 1973760 | consumed tokens: 4042260480 | elapsed time per iteration (s): 0.77 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 2.372582E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.380 | TFLOPs: 20.23 | +31: iteration 7720/ 39672 | consumed samples: 1976320 | consumed tokens: 4047503360 | elapsed time per iteration (s): 0.84 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 2.379095E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.653 | TFLOPs: 18.43 | +31: iteration 7730/ 39672 | consumed samples: 1978880 | consumed tokens: 4052746240 | elapsed time per iteration (s): 0.73 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 2.403139E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.364 | TFLOPs: 21.14 | +31: iteration 7740/ 39672 | consumed samples: 1981440 | consumed tokens: 4057989120 | elapsed time per iteration (s): 0.77 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 2.383884E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.559 | TFLOPs: 20.12 | +31: iteration 7750/ 39672 | consumed samples: 1984000 | consumed tokens: 4063232000 | elapsed time per iteration (s): 0.76 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 2.382134E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.060 | TFLOPs: 20.27 | +31: iteration 7760/ 39672 | consumed samples: 1986560 | consumed tokens: 4068474880 | elapsed time per iteration (s): 0.75 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 2.389668E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.454 | TFLOPs: 20.72 | +31: iteration 7770/ 39672 | consumed samples: 1989120 | consumed tokens: 4073717760 | elapsed time per iteration (s): 0.73 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 2.376734E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.927 | TFLOPs: 21.29 | +31: iteration 7780/ 39672 | consumed samples: 1991680 | consumed tokens: 4078960640 | elapsed time per iteration (s): 0.72 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 2.416757E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.436 | TFLOPs: 21.56 | +31: iteration 7790/ 39672 | consumed samples: 1994240 | consumed tokens: 4084203520 | elapsed time per iteration (s): 0.72 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 2.370433E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.037 | TFLOPs: 21.48 | +31: iteration 7800/ 39672 | consumed samples: 1996800 | consumed tokens: 4089446400 | elapsed time per iteration (s): 0.71 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 2.366374E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 358.803 | TFLOPs: 21.71 | +31: iteration 7810/ 39672 | consumed samples: 1999360 | consumed tokens: 4094689280 | elapsed time per iteration (s): 0.74 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 2.359543E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.697 | TFLOPs: 20.91 | +31: iteration 7820/ 39672 | consumed samples: 2001920 | consumed tokens: 4099932160 | elapsed time per iteration (s): 0.81 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 2.405234E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.156 | TFLOPs: 19.19 | +31: iteration 7830/ 39672 | consumed samples: 2004480 | consumed tokens: 4105175040 | elapsed time per iteration (s): 0.80 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 2.361013E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.311 | TFLOPs: 19.32 | +31: iteration 7840/ 39672 | consumed samples: 2007040 | consumed tokens: 4110417920 | elapsed time per iteration (s): 0.75 | learning rate: 1.845E-04 | global batch size: 256 | lm loss: 2.358178E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.088 | TFLOPs: 20.63 | +31: iteration 7850/ 39672 | consumed samples: 2009600 | consumed tokens: 4115660800 | elapsed time per iteration (s): 0.76 | learning rate: 1.845E-04 | global batch size: 256 | lm loss: 2.397744E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.392 | TFLOPs: 20.47 | +31: iteration 7860/ 39672 | consumed samples: 2012160 | consumed tokens: 4120903680 | elapsed time per iteration (s): 0.80 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 2.360566E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.396 | TFLOPs: 19.26 | +31: iteration 7870/ 39672 | consumed samples: 2014720 | consumed tokens: 4126146560 | elapsed time per iteration (s): 0.79 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 2.383508E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.494 | TFLOPs: 19.51 | +31: iteration 7880/ 39672 | consumed samples: 2017280 | consumed tokens: 4131389440 | elapsed time per iteration (s): 0.75 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 2.365379E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.160 | TFLOPs: 20.64 | +31: iteration 7890/ 39672 | consumed samples: 2019840 | consumed tokens: 4136632320 | elapsed time per iteration (s): 0.73 | learning rate: 1.843E-04 | global batch size: 256 | lm loss: 2.369596E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.847 | TFLOPs: 21.10 | +31: iteration 7900/ 39672 | consumed samples: 2022400 | consumed tokens: 4141875200 | elapsed time per iteration (s): 0.77 | learning rate: 1.843E-04 | global batch size: 256 | lm loss: 2.345848E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.909 | TFLOPs: 20.02 | +31: iteration 7910/ 39672 | consumed samples: 2024960 | consumed tokens: 4147118080 | elapsed time per iteration (s): 0.77 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 2.392186E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.481 | TFLOPs: 20.11 | +31: iteration 7920/ 39672 | consumed samples: 2027520 | consumed tokens: 4152360960 | elapsed time per iteration (s): 0.78 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 2.355175E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.425 | TFLOPs: 19.81 | +31: iteration 7930/ 39672 | consumed samples: 2030080 | consumed tokens: 4157603840 | elapsed time per iteration (s): 0.83 | learning rate: 1.841E-04 | global batch size: 256 | lm loss: 2.398930E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.811 | TFLOPs: 18.56 | +31: iteration 7940/ 39672 | consumed samples: 2032640 | consumed tokens: 4162846720 | elapsed time per iteration (s): 0.79 | learning rate: 1.841E-04 | global batch size: 256 | lm loss: 2.340562E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.499 | TFLOPs: 19.51 | +31: iteration 7950/ 39672 | consumed samples: 2035200 | consumed tokens: 4168089600 | elapsed time per iteration (s): 0.76 | learning rate: 1.841E-04 | global batch size: 256 | lm loss: 2.343592E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.817 | TFLOPs: 20.32 | +31: iteration 7960/ 39672 | consumed samples: 2037760 | consumed tokens: 4173332480 | elapsed time per iteration (s): 0.78 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 2.413305E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.546 | TFLOPs: 19.94 | +31: iteration 7970/ 39672 | consumed samples: 2040320 | consumed tokens: 4178575360 | elapsed time per iteration (s): 0.77 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 2.378253E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.127 | TFLOPs: 20.15 | +31: iteration 7980/ 39672 | consumed samples: 2042880 | consumed tokens: 4183818240 | elapsed time per iteration (s): 0.79 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 2.369498E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.157 | TFLOPs: 19.67 | +31: iteration 7990/ 39672 | consumed samples: 2045440 | consumed tokens: 4189061120 | elapsed time per iteration (s): 0.72 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 2.403040E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.475 | TFLOPs: 21.57 | + 0: [2022-11-30 11:00:46,573] [INFO] [logging.py:68:log_dist] [Rank 0] step=8000, skipped=0, lr=[0.00018386278871867934, 0.00018386278871867934, 0.00018386278871867934], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 8000/ 39672 | consumed samples: 2048000 | consumed tokens: 4194304000 | elapsed time per iteration (s): 0.79 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 2.368741E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.021 | TFLOPs: 19.66 | + 0: steps: 8000 loss: 2.3652 iter time (s): 0.782 samples/sec: 327.185 +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 8000 | lm loss value: 2.354915E+00 | lm loss PPL: 1.053723E+01 | +31: ------------------------------------------------------------------------------------------ +31: iteration 8010/ 39672 | consumed samples: 2050560 | consumed tokens: 4199546880 | elapsed time per iteration (s): 0.80 | learning rate: 1.838E-04 | global batch size: 256 | lm loss: 2.395521E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.489 | TFLOPs: 19.45 | +31: iteration 8020/ 39672 | consumed samples: 2053120 | consumed tokens: 4204789760 | elapsed time per iteration (s): 0.76 | learning rate: 1.838E-04 | global batch size: 256 | lm loss: 2.364091E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.493 | TFLOPs: 20.42 | +31: iteration 8030/ 39672 | consumed samples: 2055680 | consumed tokens: 4210032640 | elapsed time per iteration (s): 0.76 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 2.355806E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.027 | TFLOPs: 20.33 | +31: iteration 8040/ 39672 | consumed samples: 2058240 | consumed tokens: 4215275520 | elapsed time per iteration (s): 0.78 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 2.363609E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.337 | TFLOPs: 19.86 | +31: iteration 8050/ 39672 | consumed samples: 2060800 | consumed tokens: 4220518400 | elapsed time per iteration (s): 0.74 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 2.350996E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.764 | TFLOPs: 20.86 | +31: iteration 8060/ 39672 | consumed samples: 2063360 | consumed tokens: 4225761280 | elapsed time per iteration (s): 0.77 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 2.394767E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.757 | TFLOPs: 20.19 | +31: iteration 8070/ 39672 | consumed samples: 2065920 | consumed tokens: 4231004160 | elapsed time per iteration (s): 0.75 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 2.352768E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.168 | TFLOPs: 20.64 | +31: iteration 8080/ 39672 | consumed samples: 2068480 | consumed tokens: 4236247040 | elapsed time per iteration (s): 0.79 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 2.352420E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.522 | TFLOPs: 19.57 | +31: iteration 8090/ 39672 | consumed samples: 2071040 | consumed tokens: 4241489920 | elapsed time per iteration (s): 0.74 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 2.345853E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.909 | TFLOPs: 20.81 | +31: iteration 8100/ 39672 | consumed samples: 2073600 | consumed tokens: 4246732800 | elapsed time per iteration (s): 0.81 | learning rate: 1.834E-04 | global batch size: 256 | lm loss: 2.368176E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.981 | TFLOPs: 19.18 | +31: iteration 8110/ 39672 | consumed samples: 2076160 | consumed tokens: 4251975680 | elapsed time per iteration (s): 0.78 | learning rate: 1.834E-04 | global batch size: 256 | lm loss: 2.355409E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.934 | TFLOPs: 19.78 | +31: iteration 8120/ 39672 | consumed samples: 2078720 | consumed tokens: 4257218560 | elapsed time per iteration (s): 0.74 | learning rate: 1.834E-04 | global batch size: 256 | lm loss: 2.360148E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.069 | TFLOPs: 20.94 | +31: iteration 8130/ 39672 | consumed samples: 2081280 | consumed tokens: 4262461440 | elapsed time per iteration (s): 0.76 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 2.360382E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.788 | TFLOPs: 20.50 | +31: iteration 8140/ 39672 | consumed samples: 2083840 | consumed tokens: 4267704320 | elapsed time per iteration (s): 0.78 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 2.378472E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.134 | TFLOPs: 19.73 | +31: iteration 8150/ 39672 | consumed samples: 2086400 | consumed tokens: 4272947200 | elapsed time per iteration (s): 0.73 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 2.360411E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.273 | TFLOPs: 21.31 | +31: iteration 8160/ 39672 | consumed samples: 2088960 | consumed tokens: 4278190080 | elapsed time per iteration (s): 0.79 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 2.378392E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.323 | TFLOPs: 19.68 | +31: iteration 8170/ 39672 | consumed samples: 2091520 | consumed tokens: 4283432960 | elapsed time per iteration (s): 0.74 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 2.359847E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.974 | TFLOPs: 20.93 | +31: iteration 8180/ 39672 | consumed samples: 2094080 | consumed tokens: 4288675840 | elapsed time per iteration (s): 0.78 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 2.352629E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.359 | TFLOPs: 19.74 | +31: iteration 8190/ 39672 | consumed samples: 2096640 | consumed tokens: 4293918720 | elapsed time per iteration (s): 0.78 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 2.383283E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.474 | TFLOPs: 19.81 | +31: iteration 8200/ 39672 | consumed samples: 2099200 | consumed tokens: 4299161600 | elapsed time per iteration (s): 0.83 | learning rate: 1.830E-04 | global batch size: 256 | lm loss: 2.417191E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.850 | TFLOPs: 18.68 | +31: iteration 8210/ 39672 | consumed samples: 2101760 | consumed tokens: 4304404480 | elapsed time per iteration (s): 0.79 | learning rate: 1.830E-04 | global batch size: 256 | lm loss: 2.373963E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.861 | TFLOPs: 19.65 | +31: iteration 8220/ 39672 | consumed samples: 2104320 | consumed tokens: 4309647360 | elapsed time per iteration (s): 0.81 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 2.363028E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.740 | TFLOPs: 19.16 | +31: iteration 8230/ 39672 | consumed samples: 2106880 | consumed tokens: 4314890240 | elapsed time per iteration (s): 0.73 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 2.332799E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.420 | TFLOPs: 21.14 | +31: iteration 8240/ 39672 | consumed samples: 2109440 | consumed tokens: 4320133120 | elapsed time per iteration (s): 0.76 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 2.359846E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.837 | TFLOPs: 20.50 | +31: iteration 8250/ 39672 | consumed samples: 2112000 | consumed tokens: 4325376000 | elapsed time per iteration (s): 0.77 | learning rate: 1.828E-04 | global batch size: 256 | lm loss: 2.388598E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.501 | TFLOPs: 19.99 | +31: iteration 8260/ 39672 | consumed samples: 2114560 | consumed tokens: 4330618880 | elapsed time per iteration (s): 0.76 | learning rate: 1.828E-04 | global batch size: 256 | lm loss: 2.368965E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.827 | TFLOPs: 20.26 | +31: iteration 8270/ 39672 | consumed samples: 2117120 | consumed tokens: 4335861760 | elapsed time per iteration (s): 0.75 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 2.363312E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.018 | TFLOPs: 20.75 | +31: iteration 8280/ 39672 | consumed samples: 2119680 | consumed tokens: 4341104640 | elapsed time per iteration (s): 0.79 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 2.356531E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.500 | TFLOPs: 19.51 | +31: iteration 8290/ 39672 | consumed samples: 2122240 | consumed tokens: 4346347520 | elapsed time per iteration (s): 0.75 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 2.403479E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.967 | TFLOPs: 20.75 | +31: iteration 8300/ 39672 | consumed samples: 2124800 | consumed tokens: 4351590400 | elapsed time per iteration (s): 0.77 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 2.376112E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.997 | TFLOPs: 20.09 | +31: iteration 8310/ 39672 | consumed samples: 2127360 | consumed tokens: 4356833280 | elapsed time per iteration (s): 0.72 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 2.354740E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.503 | TFLOPs: 21.39 | +31: iteration 8320/ 39672 | consumed samples: 2129920 | consumed tokens: 4362076160 | elapsed time per iteration (s): 0.76 | learning rate: 1.825E-04 | global batch size: 256 | lm loss: 2.395084E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.149 | TFLOPs: 20.34 | +31: iteration 8330/ 39672 | consumed samples: 2132480 | consumed tokens: 4367319040 | elapsed time per iteration (s): 0.76 | learning rate: 1.825E-04 | global batch size: 256 | lm loss: 2.389238E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.607 | TFLOPs: 20.42 | +31: iteration 8340/ 39672 | consumed samples: 2135040 | consumed tokens: 4372561920 | elapsed time per iteration (s): 0.78 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 2.389019E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.680 | TFLOPs: 19.94 | +31: iteration 8350/ 39672 | consumed samples: 2137600 | consumed tokens: 4377804800 | elapsed time per iteration (s): 0.74 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 2.367454E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.213 | TFLOPs: 20.88 | +31: iteration 8360/ 39672 | consumed samples: 2140160 | consumed tokens: 4383047680 | elapsed time per iteration (s): 0.82 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 2.372753E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.031 | TFLOPs: 18.82 | +31: iteration 8370/ 39672 | consumed samples: 2142720 | consumed tokens: 4388290560 | elapsed time per iteration (s): 0.79 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 2.331334E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.927 | TFLOPs: 19.72 | +31: iteration 8380/ 39672 | consumed samples: 2145280 | consumed tokens: 4393533440 | elapsed time per iteration (s): 0.82 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 2.357254E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.835 | TFLOPs: 18.80 | +31: iteration 8390/ 39672 | consumed samples: 2147840 | consumed tokens: 4398776320 | elapsed time per iteration (s): 0.79 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 2.352776E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.211 | TFLOPs: 19.67 | +31: iteration 8400/ 39672 | consumed samples: 2150400 | consumed tokens: 4404019200 | elapsed time per iteration (s): 0.82 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 2.334625E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.450 | TFLOPs: 18.96 | +31: iteration 8410/ 39672 | consumed samples: 2152960 | consumed tokens: 4409262080 | elapsed time per iteration (s): 0.80 | learning rate: 1.821E-04 | global batch size: 256 | lm loss: 2.319362E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.515 | TFLOPs: 19.33 | +31: iteration 8420/ 39672 | consumed samples: 2155520 | consumed tokens: 4414504960 | elapsed time per iteration (s): 0.80 | learning rate: 1.821E-04 | global batch size: 256 | lm loss: 2.341407E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.011 | TFLOPs: 19.36 | +31: iteration 8430/ 39672 | consumed samples: 2158080 | consumed tokens: 4419747840 | elapsed time per iteration (s): 0.81 | learning rate: 1.821E-04 | global batch size: 256 | lm loss: 2.371406E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.594 | TFLOPs: 19.03 | +31: iteration 8440/ 39672 | consumed samples: 2160640 | consumed tokens: 4424990720 | elapsed time per iteration (s): 0.83 | learning rate: 1.820E-04 | global batch size: 256 | lm loss: 2.351351E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.589 | TFLOPs: 18.55 | +31: iteration 8450/ 39672 | consumed samples: 2163200 | consumed tokens: 4430233600 | elapsed time per iteration (s): 0.83 | learning rate: 1.820E-04 | global batch size: 256 | lm loss: 2.361065E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.875 | TFLOPs: 18.69 | +31: iteration 8460/ 39672 | consumed samples: 2165760 | consumed tokens: 4435476480 | elapsed time per iteration (s): 0.81 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 2.382708E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.097 | TFLOPs: 19.12 | +31: iteration 8470/ 39672 | consumed samples: 2168320 | consumed tokens: 4440719360 | elapsed time per iteration (s): 0.80 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 2.344211E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.797 | TFLOPs: 19.29 | +31: iteration 8480/ 39672 | consumed samples: 2170880 | consumed tokens: 4445962240 | elapsed time per iteration (s): 0.81 | learning rate: 1.818E-04 | global batch size: 256 | lm loss: 2.341878E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.556 | TFLOPs: 19.09 | +31: iteration 8490/ 39672 | consumed samples: 2173440 | consumed tokens: 4451205120 | elapsed time per iteration (s): 0.76 | learning rate: 1.818E-04 | global batch size: 256 | lm loss: 2.367919E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.420 | TFLOPs: 20.47 | +31: iteration 8500/ 39672 | consumed samples: 2176000 | consumed tokens: 4456448000 | elapsed time per iteration (s): 0.78 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 2.371237E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.692 | TFLOPs: 19.95 | +31: iteration 8510/ 39672 | consumed samples: 2178560 | consumed tokens: 4461690880 | elapsed time per iteration (s): 0.83 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 2.310388E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.719 | TFLOPs: 18.74 | +31: iteration 8520/ 39672 | consumed samples: 2181120 | consumed tokens: 4466933760 | elapsed time per iteration (s): 0.79 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 2.335310E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.039 | TFLOPs: 19.48 | +31: iteration 8530/ 39672 | consumed samples: 2183680 | consumed tokens: 4472176640 | elapsed time per iteration (s): 0.82 | learning rate: 1.816E-04 | global batch size: 256 | lm loss: 2.339543E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.714 | TFLOPs: 18.98 | +31: iteration 8540/ 39672 | consumed samples: 2186240 | consumed tokens: 4477419520 | elapsed time per iteration (s): 0.82 | learning rate: 1.816E-04 | global batch size: 256 | lm loss: 2.349662E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.648 | TFLOPs: 18.91 | +31: iteration 8550/ 39672 | consumed samples: 2188800 | consumed tokens: 4482662400 | elapsed time per iteration (s): 0.82 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 2.346441E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.614 | TFLOPs: 18.97 | +31: iteration 8560/ 39672 | consumed samples: 2191360 | consumed tokens: 4487905280 | elapsed time per iteration (s): 0.79 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 2.356338E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.983 | TFLOPs: 19.72 | +31: iteration 8570/ 39672 | consumed samples: 2193920 | consumed tokens: 4493148160 | elapsed time per iteration (s): 0.81 | learning rate: 1.814E-04 | global batch size: 256 | lm loss: 2.350488E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.480 | TFLOPs: 19.09 | +31: iteration 8580/ 39672 | consumed samples: 2196480 | consumed tokens: 4498391040 | elapsed time per iteration (s): 0.82 | learning rate: 1.814E-04 | global batch size: 256 | lm loss: 2.352690E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.087 | TFLOPs: 18.82 | +31: iteration 8590/ 39672 | consumed samples: 2199040 | consumed tokens: 4503633920 | elapsed time per iteration (s): 0.82 | learning rate: 1.814E-04 | global batch size: 256 | lm loss: 2.379268E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.263 | TFLOPs: 18.89 | +31: iteration 8600/ 39672 | consumed samples: 2201600 | consumed tokens: 4508876800 | elapsed time per iteration (s): 0.81 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 2.367188E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.358 | TFLOPs: 19.20 | +31: iteration 8610/ 39672 | consumed samples: 2204160 | consumed tokens: 4514119680 | elapsed time per iteration (s): 0.82 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 2.342593E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.999 | TFLOPs: 19.00 | +31: iteration 8620/ 39672 | consumed samples: 2206720 | consumed tokens: 4519362560 | elapsed time per iteration (s): 0.80 | learning rate: 1.812E-04 | global batch size: 256 | lm loss: 2.378980E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.845 | TFLOPs: 19.35 | +31: iteration 8630/ 39672 | consumed samples: 2209280 | consumed tokens: 4524605440 | elapsed time per iteration (s): 0.79 | learning rate: 1.812E-04 | global batch size: 256 | lm loss: 2.335683E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.860 | TFLOPs: 19.71 | +31: iteration 8640/ 39672 | consumed samples: 2211840 | consumed tokens: 4529848320 | elapsed time per iteration (s): 0.81 | learning rate: 1.811E-04 | global batch size: 256 | lm loss: 2.327373E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.517 | TFLOPs: 19.15 | +31: iteration 8650/ 39672 | consumed samples: 2214400 | consumed tokens: 4535091200 | elapsed time per iteration (s): 0.81 | learning rate: 1.811E-04 | global batch size: 256 | lm loss: 2.321798E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.014 | TFLOPs: 19.18 | +31: iteration 8660/ 39672 | consumed samples: 2216960 | consumed tokens: 4540334080 | elapsed time per iteration (s): 0.80 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 2.354876E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.735 | TFLOPs: 19.40 | +31: iteration 8670/ 39672 | consumed samples: 2219520 | consumed tokens: 4545576960 | elapsed time per iteration (s): 0.78 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 2.345911E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.791 | TFLOPs: 19.83 | +31: iteration 8680/ 39672 | consumed samples: 2222080 | consumed tokens: 4550819840 | elapsed time per iteration (s): 0.84 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 2.345838E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.979 | TFLOPs: 18.39 | +31: iteration 8690/ 39672 | consumed samples: 2224640 | consumed tokens: 4556062720 | elapsed time per iteration (s): 0.84 | learning rate: 1.809E-04 | global batch size: 256 | lm loss: 2.333800E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.181 | TFLOPs: 18.34 | +31: iteration 8700/ 39672 | consumed samples: 2227200 | consumed tokens: 4561305600 | elapsed time per iteration (s): 0.85 | learning rate: 1.809E-04 | global batch size: 256 | lm loss: 2.342756E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.096 | TFLOPs: 18.28 | +31: iteration 8710/ 39672 | consumed samples: 2229760 | consumed tokens: 4566548480 | elapsed time per iteration (s): 0.84 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 2.329661E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.962 | TFLOPs: 18.33 | +31: iteration 8720/ 39672 | consumed samples: 2232320 | consumed tokens: 4571791360 | elapsed time per iteration (s): 0.83 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 2.337403E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.005 | TFLOPs: 18.75 | +31: iteration 8730/ 39672 | consumed samples: 2234880 | consumed tokens: 4577034240 | elapsed time per iteration (s): 0.79 | learning rate: 1.807E-04 | global batch size: 256 | lm loss: 2.377351E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.115 | TFLOPs: 19.61 | +31: iteration 8740/ 39672 | consumed samples: 2237440 | consumed tokens: 4582277120 | elapsed time per iteration (s): 0.81 | learning rate: 1.807E-04 | global batch size: 256 | lm loss: 2.319997E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.015 | TFLOPs: 19.12 | +31: iteration 8750/ 39672 | consumed samples: 2240000 | consumed tokens: 4587520000 | elapsed time per iteration (s): 0.82 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 2.360958E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.383 | TFLOPs: 18.96 | +31: iteration 8760/ 39672 | consumed samples: 2242560 | consumed tokens: 4592762880 | elapsed time per iteration (s): 0.85 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 2.348904E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.503 | TFLOPs: 18.12 | +31: iteration 8770/ 39672 | consumed samples: 2245120 | consumed tokens: 4598005760 | elapsed time per iteration (s): 0.82 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 2.321353E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.032 | TFLOPs: 19.00 | +31: iteration 8780/ 39672 | consumed samples: 2247680 | consumed tokens: 4603248640 | elapsed time per iteration (s): 0.80 | learning rate: 1.805E-04 | global batch size: 256 | lm loss: 2.762987E+00 | grad norm: 5.885 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.519 | TFLOPs: 19.45 | +31: iteration 8790/ 39672 | consumed samples: 2250240 | consumed tokens: 4608491520 | elapsed time per iteration (s): 0.82 | learning rate: 1.805E-04 | global batch size: 256 | lm loss: 3.313927E+00 | grad norm: 17.690 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.531 | TFLOPs: 18.91 | +31: iteration 8800/ 39672 | consumed samples: 2252800 | consumed tokens: 4613734400 | elapsed time per iteration (s): 0.81 | learning rate: 1.804E-04 | global batch size: 256 | lm loss: 2.972519E+00 | grad norm: 4.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.392 | TFLOPs: 19.08 | +31: iteration 8810/ 39672 | consumed samples: 2255360 | consumed tokens: 4618977280 | elapsed time per iteration (s): 0.82 | learning rate: 1.804E-04 | global batch size: 256 | lm loss: 2.676852E+00 | grad norm: 0.850 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.490 | TFLOPs: 18.97 | +31: iteration 8820/ 39672 | consumed samples: 2257920 | consumed tokens: 4624220160 | elapsed time per iteration (s): 0.81 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 2.523177E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.631 | TFLOPs: 19.22 | +31: iteration 8830/ 39672 | consumed samples: 2260480 | consumed tokens: 4629463040 | elapsed time per iteration (s): 0.83 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 2.441663E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.038 | TFLOPs: 18.64 | +31: iteration 8840/ 39672 | consumed samples: 2263040 | consumed tokens: 4634705920 | elapsed time per iteration (s): 0.84 | learning rate: 1.802E-04 | global batch size: 256 | lm loss: 2.414252E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.118 | TFLOPs: 18.46 | +31: iteration 8850/ 39672 | consumed samples: 2265600 | consumed tokens: 4639948800 | elapsed time per iteration (s): 0.79 | learning rate: 1.802E-04 | global batch size: 256 | lm loss: 2.379869E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.840 | TFLOPs: 19.53 | +31: iteration 8860/ 39672 | consumed samples: 2268160 | consumed tokens: 4645191680 | elapsed time per iteration (s): 0.81 | learning rate: 1.802E-04 | global batch size: 256 | lm loss: 2.381103E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.991 | TFLOPs: 19.18 | +31: iteration 8870/ 39672 | consumed samples: 2270720 | consumed tokens: 4650434560 | elapsed time per iteration (s): 0.81 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 2.353841E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.236 | TFLOPs: 19.19 | +31: iteration 8880/ 39672 | consumed samples: 2273280 | consumed tokens: 4655677440 | elapsed time per iteration (s): 0.75 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 2.362630E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.625 | TFLOPs: 20.55 | +31: iteration 8890/ 39672 | consumed samples: 2275840 | consumed tokens: 4660920320 | elapsed time per iteration (s): 0.71 | learning rate: 1.800E-04 | global batch size: 256 | lm loss: 2.338124E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 358.636 | TFLOPs: 21.70 | +31: iteration 8900/ 39672 | consumed samples: 2278400 | consumed tokens: 4666163200 | elapsed time per iteration (s): 0.74 | learning rate: 1.800E-04 | global batch size: 256 | lm loss: 2.367027E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.279 | TFLOPs: 20.83 | +31: iteration 8910/ 39672 | consumed samples: 2280960 | consumed tokens: 4671406080 | elapsed time per iteration (s): 0.77 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 2.356535E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.710 | TFLOPs: 20.19 | +31: iteration 8920/ 39672 | consumed samples: 2283520 | consumed tokens: 4676648960 | elapsed time per iteration (s): 0.79 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 2.336300E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.503 | TFLOPs: 19.51 | +31: iteration 8930/ 39672 | consumed samples: 2286080 | consumed tokens: 4681891840 | elapsed time per iteration (s): 0.74 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 2.343324E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.220 | TFLOPs: 20.88 | +31: iteration 8940/ 39672 | consumed samples: 2288640 | consumed tokens: 4687134720 | elapsed time per iteration (s): 0.75 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 2.341087E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.456 | TFLOPs: 20.60 | +31: iteration 8950/ 39672 | consumed samples: 2291200 | consumed tokens: 4692377600 | elapsed time per iteration (s): 0.82 | learning rate: 1.797E-04 | global batch size: 256 | lm loss: 2.350762E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.966 | TFLOPs: 18.87 | +31: iteration 8960/ 39672 | consumed samples: 2293760 | consumed tokens: 4697620480 | elapsed time per iteration (s): 0.80 | learning rate: 1.797E-04 | global batch size: 256 | lm loss: 2.340655E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.128 | TFLOPs: 19.37 | +31: iteration 8970/ 39672 | consumed samples: 2296320 | consumed tokens: 4702863360 | elapsed time per iteration (s): 0.77 | learning rate: 1.797E-04 | global batch size: 256 | lm loss: 2.347279E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.797 | TFLOPs: 20.19 | +31: iteration 8980/ 39672 | consumed samples: 2298880 | consumed tokens: 4708106240 | elapsed time per iteration (s): 0.75 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 2.328112E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.310 | TFLOPs: 20.59 | +31: iteration 8990/ 39672 | consumed samples: 2301440 | consumed tokens: 4713349120 | elapsed time per iteration (s): 0.80 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 2.335209E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.073 | TFLOPs: 19.30 | +31: iteration 9000/ 39672 | consumed samples: 2304000 | consumed tokens: 4718592000 | elapsed time per iteration (s): 0.83 | learning rate: 1.795E-04 | global batch size: 256 | lm loss: 2.341306E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.677 | TFLOPs: 18.55 | +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 9000 | lm loss value: 2.238359E+00 | lm loss PPL: 9.377927E+00 | +31: ------------------------------------------------------------------------------------------ +31: iteration 9010/ 39672 | consumed samples: 2306560 | consumed tokens: 4723834880 | elapsed time per iteration (s): 0.85 | learning rate: 1.795E-04 | global batch size: 256 | lm loss: 2.358199E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.388 | TFLOPs: 18.23 | +31: iteration 9020/ 39672 | consumed samples: 2309120 | consumed tokens: 4729077760 | elapsed time per iteration (s): 0.84 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 2.332387E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.117 | TFLOPs: 18.40 | +31: iteration 9030/ 39672 | consumed samples: 2311680 | consumed tokens: 4734320640 | elapsed time per iteration (s): 0.83 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 2.361987E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.080 | TFLOPs: 18.76 | +31: iteration 9040/ 39672 | consumed samples: 2314240 | consumed tokens: 4739563520 | elapsed time per iteration (s): 0.78 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 2.351774E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.197 | TFLOPs: 19.73 | +31: iteration 9050/ 39672 | consumed samples: 2316800 | consumed tokens: 4744806400 | elapsed time per iteration (s): 0.81 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 2.366841E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.893 | TFLOPs: 19.23 | +31: iteration 9060/ 39672 | consumed samples: 2319360 | consumed tokens: 4750049280 | elapsed time per iteration (s): 0.78 | learning rate: 1.792E-04 | global batch size: 256 | lm loss: 2.361138E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.518 | TFLOPs: 19.81 | +31: iteration 9070/ 39672 | consumed samples: 2321920 | consumed tokens: 4755292160 | elapsed time per iteration (s): 0.81 | learning rate: 1.792E-04 | global batch size: 256 | lm loss: 2.346061E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.896 | TFLOPs: 19.23 | +31: iteration 9080/ 39672 | consumed samples: 2324480 | consumed tokens: 4760535040 | elapsed time per iteration (s): 0.80 | learning rate: 1.792E-04 | global batch size: 256 | lm loss: 2.371458E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.772 | TFLOPs: 19.47 | +31: iteration 9090/ 39672 | consumed samples: 2327040 | consumed tokens: 4765777920 | elapsed time per iteration (s): 0.81 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 2.329814E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.863 | TFLOPs: 19.17 | +31: iteration 9100/ 39672 | consumed samples: 2329600 | consumed tokens: 4771020800 | elapsed time per iteration (s): 0.80 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 2.354848E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.307 | TFLOPs: 19.32 | +31: iteration 9110/ 39672 | consumed samples: 2332160 | consumed tokens: 4776263680 | elapsed time per iteration (s): 0.84 | learning rate: 1.790E-04 | global batch size: 256 | lm loss: 2.322431E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.274 | TFLOPs: 18.41 | +31: iteration 9120/ 39672 | consumed samples: 2334720 | consumed tokens: 4781506560 | elapsed time per iteration (s): 0.80 | learning rate: 1.790E-04 | global batch size: 256 | lm loss: 2.350804E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.053 | TFLOPs: 19.42 | +31: iteration 9130/ 39672 | consumed samples: 2337280 | consumed tokens: 4786749440 | elapsed time per iteration (s): 0.81 | learning rate: 1.789E-04 | global batch size: 256 | lm loss: 2.345315E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.734 | TFLOPs: 19.22 | +31: iteration 9140/ 39672 | consumed samples: 2339840 | consumed tokens: 4791992320 | elapsed time per iteration (s): 0.78 | learning rate: 1.789E-04 | global batch size: 256 | lm loss: 2.338675E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.234 | TFLOPs: 19.98 | +31: iteration 9150/ 39672 | consumed samples: 2342400 | consumed tokens: 4797235200 | elapsed time per iteration (s): 0.85 | learning rate: 1.788E-04 | global batch size: 256 | lm loss: 2.398764E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.957 | TFLOPs: 18.27 | +31: iteration 9160/ 39672 | consumed samples: 2344960 | consumed tokens: 4802478080 | elapsed time per iteration (s): 0.80 | learning rate: 1.788E-04 | global batch size: 256 | lm loss: 2.392581E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.113 | TFLOPs: 19.31 | +31: iteration 9170/ 39672 | consumed samples: 2347520 | consumed tokens: 4807720960 | elapsed time per iteration (s): 0.81 | learning rate: 1.787E-04 | global batch size: 256 | lm loss: 2.412263E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.731 | TFLOPs: 19.16 | +31: iteration 9180/ 39672 | consumed samples: 2350080 | consumed tokens: 4812963840 | elapsed time per iteration (s): 0.77 | learning rate: 1.787E-04 | global batch size: 256 | lm loss: 2.361541E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.451 | TFLOPs: 20.05 | +31: iteration 9190/ 39672 | consumed samples: 2352640 | consumed tokens: 4818206720 | elapsed time per iteration (s): 0.84 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 2.359732E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.754 | TFLOPs: 18.38 | +31: iteration 9200/ 39672 | consumed samples: 2355200 | consumed tokens: 4823449600 | elapsed time per iteration (s): 0.82 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 2.343287E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.191 | TFLOPs: 18.89 | +31: iteration 9210/ 39672 | consumed samples: 2357760 | consumed tokens: 4828692480 | elapsed time per iteration (s): 0.77 | learning rate: 1.785E-04 | global batch size: 256 | lm loss: 2.337670E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.518 | TFLOPs: 20.24 | +31: iteration 9220/ 39672 | consumed samples: 2360320 | consumed tokens: 4833935360 | elapsed time per iteration (s): 0.78 | learning rate: 1.785E-04 | global batch size: 256 | lm loss: 2.295063E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.080 | TFLOPs: 19.79 | +31: iteration 9230/ 39672 | consumed samples: 2362880 | consumed tokens: 4839178240 | elapsed time per iteration (s): 0.75 | learning rate: 1.785E-04 | global batch size: 256 | lm loss: 2.355652E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.267 | TFLOPs: 20.65 | +31: iteration 9240/ 39672 | consumed samples: 2365440 | consumed tokens: 4844421120 | elapsed time per iteration (s): 0.74 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 2.340256E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.037 | TFLOPs: 20.87 | +31: iteration 9250/ 39672 | consumed samples: 2368000 | consumed tokens: 4849664000 | elapsed time per iteration (s): 0.74 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 2.336010E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.717 | TFLOPs: 20.91 | +31: iteration 9260/ 39672 | consumed samples: 2370560 | consumed tokens: 4854906880 | elapsed time per iteration (s): 0.76 | learning rate: 1.783E-04 | global batch size: 256 | lm loss: 2.365745E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.540 | TFLOPs: 20.48 | +31: iteration 9270/ 39672 | consumed samples: 2373120 | consumed tokens: 4860149760 | elapsed time per iteration (s): 0.74 | learning rate: 1.783E-04 | global batch size: 256 | lm loss: 2.352321E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.635 | TFLOPs: 20.79 | +31: iteration 9280/ 39672 | consumed samples: 2375680 | consumed tokens: 4865392640 | elapsed time per iteration (s): 0.71 | learning rate: 1.782E-04 | global batch size: 256 | lm loss: 2.352668E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.798 | TFLOPs: 21.77 | +31: iteration 9290/ 39672 | consumed samples: 2378240 | consumed tokens: 4870635520 | elapsed time per iteration (s): 0.74 | learning rate: 1.782E-04 | global batch size: 256 | lm loss: 2.337862E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.384 | TFLOPs: 20.83 | +31: iteration 9300/ 39672 | consumed samples: 2380800 | consumed tokens: 4875878400 | elapsed time per iteration (s): 0.73 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 2.322703E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.063 | TFLOPs: 21.30 | +31: iteration 9310/ 39672 | consumed samples: 2383360 | consumed tokens: 4881121280 | elapsed time per iteration (s): 0.73 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 2.339590E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.535 | TFLOPs: 21.27 | +31: iteration 9320/ 39672 | consumed samples: 2385920 | consumed tokens: 4886364160 | elapsed time per iteration (s): 0.73 | learning rate: 1.780E-04 | global batch size: 256 | lm loss: 2.336582E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.429 | TFLOPs: 21.08 | +31: iteration 9330/ 39672 | consumed samples: 2388480 | consumed tokens: 4891607040 | elapsed time per iteration (s): 0.82 | learning rate: 1.780E-04 | global batch size: 256 | lm loss: 2.364060E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.004 | TFLOPs: 18.81 | +31: iteration 9340/ 39672 | consumed samples: 2391040 | consumed tokens: 4896849920 | elapsed time per iteration (s): 0.74 | learning rate: 1.779E-04 | global batch size: 256 | lm loss: 2.347549E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.792 | TFLOPs: 20.98 | +31: iteration 9350/ 39672 | consumed samples: 2393600 | consumed tokens: 4902092800 | elapsed time per iteration (s): 0.78 | learning rate: 1.779E-04 | global batch size: 256 | lm loss: 2.348902E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.294 | TFLOPs: 19.86 | +31: iteration 9360/ 39672 | consumed samples: 2396160 | consumed tokens: 4907335680 | elapsed time per iteration (s): 0.80 | learning rate: 1.778E-04 | global batch size: 256 | lm loss: 2.305205E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.256 | TFLOPs: 19.25 | +31: iteration 9370/ 39672 | consumed samples: 2398720 | consumed tokens: 4912578560 | elapsed time per iteration (s): 0.75 | learning rate: 1.778E-04 | global batch size: 256 | lm loss: 2.327639E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.616 | TFLOPs: 20.73 | +31: iteration 9380/ 39672 | consumed samples: 2401280 | consumed tokens: 4917821440 | elapsed time per iteration (s): 0.76 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 2.345480E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.872 | TFLOPs: 20.44 | +31: iteration 9390/ 39672 | consumed samples: 2403840 | consumed tokens: 4923064320 | elapsed time per iteration (s): 0.73 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 2.313317E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.827 | TFLOPs: 21.10 | +31: iteration 9400/ 39672 | consumed samples: 2406400 | consumed tokens: 4928307200 | elapsed time per iteration (s): 0.77 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 2.340033E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.980 | TFLOPs: 20.14 | +31: iteration 9410/ 39672 | consumed samples: 2408960 | consumed tokens: 4933550080 | elapsed time per iteration (s): 0.72 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 2.294843E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.267 | TFLOPs: 21.37 | +31: iteration 9420/ 39672 | consumed samples: 2411520 | consumed tokens: 4938792960 | elapsed time per iteration (s): 0.77 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 2.351915E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.485 | TFLOPs: 20.24 | +31: iteration 9430/ 39672 | consumed samples: 2414080 | consumed tokens: 4944035840 | elapsed time per iteration (s): 0.73 | learning rate: 1.775E-04 | global batch size: 256 | lm loss: 2.319693E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.129 | TFLOPs: 21.24 | +31: iteration 9440/ 39672 | consumed samples: 2416640 | consumed tokens: 4949278720 | elapsed time per iteration (s): 0.75 | learning rate: 1.775E-04 | global batch size: 256 | lm loss: 2.344422E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.426 | TFLOPs: 20.66 | +31: iteration 9450/ 39672 | consumed samples: 2419200 | consumed tokens: 4954521600 | elapsed time per iteration (s): 0.74 | learning rate: 1.774E-04 | global batch size: 256 | lm loss: 2.377758E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.848 | TFLOPs: 21.04 | +31: iteration 9460/ 39672 | consumed samples: 2421760 | consumed tokens: 4959764480 | elapsed time per iteration (s): 0.76 | learning rate: 1.774E-04 | global batch size: 256 | lm loss: 2.350885E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.912 | TFLOPs: 20.44 | +31: iteration 9470/ 39672 | consumed samples: 2424320 | consumed tokens: 4965007360 | elapsed time per iteration (s): 0.77 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 2.361448E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.164 | TFLOPs: 20.16 | +31: iteration 9480/ 39672 | consumed samples: 2426880 | consumed tokens: 4970250240 | elapsed time per iteration (s): 0.75 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 2.313439E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.640 | TFLOPs: 20.55 | +31: iteration 9490/ 39672 | consumed samples: 2429440 | consumed tokens: 4975493120 | elapsed time per iteration (s): 0.77 | learning rate: 1.772E-04 | global batch size: 256 | lm loss: 2.313201E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.396 | TFLOPs: 20.23 | +31: iteration 9500/ 39672 | consumed samples: 2432000 | consumed tokens: 4980736000 | elapsed time per iteration (s): 0.76 | learning rate: 1.772E-04 | global batch size: 256 | lm loss: 2.341309E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.994 | TFLOPs: 20.27 | +31: iteration 9510/ 39672 | consumed samples: 2434560 | consumed tokens: 4985978880 | elapsed time per iteration (s): 0.73 | learning rate: 1.771E-04 | global batch size: 256 | lm loss: 2.335577E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.041 | TFLOPs: 21.24 | +31: iteration 9520/ 39672 | consumed samples: 2437120 | consumed tokens: 4991221760 | elapsed time per iteration (s): 0.77 | learning rate: 1.771E-04 | global batch size: 256 | lm loss: 2.316020E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.389 | TFLOPs: 20.23 | +31: iteration 9530/ 39672 | consumed samples: 2439680 | consumed tokens: 4996464640 | elapsed time per iteration (s): 0.76 | learning rate: 1.770E-04 | global batch size: 256 | lm loss: 2.353299E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.144 | TFLOPs: 20.34 | +31: iteration 9540/ 39672 | consumed samples: 2442240 | consumed tokens: 5001707520 | elapsed time per iteration (s): 0.74 | learning rate: 1.770E-04 | global batch size: 256 | lm loss: 2.351148E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.358 | TFLOPs: 20.89 | +31: iteration 9550/ 39672 | consumed samples: 2444800 | consumed tokens: 5006950400 | elapsed time per iteration (s): 0.77 | learning rate: 1.769E-04 | global batch size: 256 | lm loss: 2.343112E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.631 | TFLOPs: 20.12 | +31: iteration 9560/ 39672 | consumed samples: 2447360 | consumed tokens: 5012193280 | elapsed time per iteration (s): 0.72 | learning rate: 1.769E-04 | global batch size: 256 | lm loss: 2.337354E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.815 | TFLOPs: 21.53 | +31: iteration 9570/ 39672 | consumed samples: 2449920 | consumed tokens: 5017436160 | elapsed time per iteration (s): 0.77 | learning rate: 1.768E-04 | global batch size: 256 | lm loss: 2.273689E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.316 | TFLOPs: 20.04 | +31: iteration 9580/ 39672 | consumed samples: 2452480 | consumed tokens: 5022679040 | elapsed time per iteration (s): 0.71 | learning rate: 1.768E-04 | global batch size: 256 | lm loss: 2.335820E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.751 | TFLOPs: 21.76 | +31: iteration 9590/ 39672 | consumed samples: 2455040 | consumed tokens: 5027921920 | elapsed time per iteration (s): 0.78 | learning rate: 1.767E-04 | global batch size: 256 | lm loss: 2.305260E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.326 | TFLOPs: 19.80 | +31: iteration 9600/ 39672 | consumed samples: 2457600 | consumed tokens: 5033164800 | elapsed time per iteration (s): 0.78 | learning rate: 1.767E-04 | global batch size: 256 | lm loss: 2.314492E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.960 | TFLOPs: 19.78 | +31: iteration 9610/ 39672 | consumed samples: 2460160 | consumed tokens: 5038407680 | elapsed time per iteration (s): 0.75 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 2.311023E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.366 | TFLOPs: 20.53 | +31: iteration 9620/ 39672 | consumed samples: 2462720 | consumed tokens: 5043650560 | elapsed time per iteration (s): 0.75 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 2.366824E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.475 | TFLOPs: 20.60 | +31: iteration 9630/ 39672 | consumed samples: 2465280 | consumed tokens: 5048893440 | elapsed time per iteration (s): 0.77 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 2.341371E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.693 | TFLOPs: 20.07 | +31: iteration 9640/ 39672 | consumed samples: 2467840 | consumed tokens: 5054136320 | elapsed time per iteration (s): 0.79 | learning rate: 1.765E-04 | global batch size: 256 | lm loss: 2.298769E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.405 | TFLOPs: 19.50 | +31: iteration 9650/ 39672 | consumed samples: 2470400 | consumed tokens: 5059379200 | elapsed time per iteration (s): 0.79 | learning rate: 1.765E-04 | global batch size: 256 | lm loss: 2.336618E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.701 | TFLOPs: 19.64 | +31: iteration 9660/ 39672 | consumed samples: 2472960 | consumed tokens: 5064622080 | elapsed time per iteration (s): 0.75 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 2.340096E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.724 | TFLOPs: 20.61 | +31: iteration 9670/ 39672 | consumed samples: 2475520 | consumed tokens: 5069864960 | elapsed time per iteration (s): 0.74 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 2.309652E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.883 | TFLOPs: 20.99 | +31: iteration 9680/ 39672 | consumed samples: 2478080 | consumed tokens: 5075107840 | elapsed time per iteration (s): 0.72 | learning rate: 1.763E-04 | global batch size: 256 | lm loss: 2.312276E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.696 | TFLOPs: 21.40 | +31: iteration 9690/ 39672 | consumed samples: 2480640 | consumed tokens: 5080350720 | elapsed time per iteration (s): 0.79 | learning rate: 1.763E-04 | global batch size: 256 | lm loss: 2.313847E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.338 | TFLOPs: 19.68 | +31: iteration 9700/ 39672 | consumed samples: 2483200 | consumed tokens: 5085593600 | elapsed time per iteration (s): 0.74 | learning rate: 1.762E-04 | global batch size: 256 | lm loss: 2.322734E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.151 | TFLOPs: 20.88 | +31: iteration 9710/ 39672 | consumed samples: 2485760 | consumed tokens: 5090836480 | elapsed time per iteration (s): 0.74 | learning rate: 1.762E-04 | global batch size: 256 | lm loss: 2.317008E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.196 | TFLOPs: 21.06 | +31: iteration 9720/ 39672 | consumed samples: 2488320 | consumed tokens: 5096079360 | elapsed time per iteration (s): 0.74 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 2.321679E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.188 | TFLOPs: 20.88 | +31: iteration 9730/ 39672 | consumed samples: 2490880 | consumed tokens: 5101322240 | elapsed time per iteration (s): 0.76 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 2.368341E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.012 | TFLOPs: 20.51 | +31: iteration 9740/ 39672 | consumed samples: 2493440 | consumed tokens: 5106565120 | elapsed time per iteration (s): 0.72 | learning rate: 1.760E-04 | global batch size: 256 | lm loss: 2.338124E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.399 | TFLOPs: 21.44 | +31: iteration 9750/ 39672 | consumed samples: 2496000 | consumed tokens: 5111808000 | elapsed time per iteration (s): 0.73 | learning rate: 1.760E-04 | global batch size: 256 | lm loss: 2.315777E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.052 | TFLOPs: 21.12 | +31: iteration 9760/ 39672 | consumed samples: 2498560 | consumed tokens: 5117050880 | elapsed time per iteration (s): 0.73 | learning rate: 1.759E-04 | global batch size: 256 | lm loss: 2.309905E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.003 | TFLOPs: 21.30 | +31: iteration 9770/ 39672 | consumed samples: 2501120 | consumed tokens: 5122293760 | elapsed time per iteration (s): 0.76 | learning rate: 1.759E-04 | global batch size: 256 | lm loss: 2.324068E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.778 | TFLOPs: 20.43 | +31: iteration 9780/ 39672 | consumed samples: 2503680 | consumed tokens: 5127536640 | elapsed time per iteration (s): 0.73 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 2.349970E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.048 | TFLOPs: 21.18 | +31: iteration 9790/ 39672 | consumed samples: 2506240 | consumed tokens: 5132779520 | elapsed time per iteration (s): 0.94 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 2.308739E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 271.434 | TFLOPs: 16.42 | +31: iteration 9800/ 39672 | consumed samples: 2508800 | consumed tokens: 5138022400 | elapsed time per iteration (s): 0.75 | learning rate: 1.757E-04 | global batch size: 256 | lm loss: 2.335761E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.513 | TFLOPs: 20.60 | +31: iteration 9810/ 39672 | consumed samples: 2511360 | consumed tokens: 5143265280 | elapsed time per iteration (s): 0.74 | learning rate: 1.757E-04 | global batch size: 256 | lm loss: 2.331250E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.468 | TFLOPs: 20.96 | +31: iteration 9820/ 39672 | consumed samples: 2513920 | consumed tokens: 5148508160 | elapsed time per iteration (s): 0.85 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 2.304967E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.392 | TFLOPs: 18.23 | +31: iteration 9830/ 39672 | consumed samples: 2516480 | consumed tokens: 5153751040 | elapsed time per iteration (s): 0.79 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 2.330375E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.015 | TFLOPs: 19.54 | +31: iteration 9840/ 39672 | consumed samples: 2519040 | consumed tokens: 5158993920 | elapsed time per iteration (s): 0.76 | learning rate: 1.755E-04 | global batch size: 256 | lm loss: 2.286175E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.948 | TFLOPs: 20.51 | +31: iteration 9850/ 39672 | consumed samples: 2521600 | consumed tokens: 5164236800 | elapsed time per iteration (s): 0.73 | learning rate: 1.755E-04 | global batch size: 256 | lm loss: 2.328745E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.732 | TFLOPs: 21.16 | +31: iteration 9860/ 39672 | consumed samples: 2524160 | consumed tokens: 5169479680 | elapsed time per iteration (s): 0.75 | learning rate: 1.754E-04 | global batch size: 256 | lm loss: 2.342237E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.651 | TFLOPs: 20.61 | +31: iteration 9870/ 39672 | consumed samples: 2526720 | consumed tokens: 5174722560 | elapsed time per iteration (s): 0.74 | learning rate: 1.754E-04 | global batch size: 256 | lm loss: 2.290962E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.269 | TFLOPs: 21.01 | +31: iteration 9880/ 39672 | consumed samples: 2529280 | consumed tokens: 5179965440 | elapsed time per iteration (s): 0.80 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 2.320225E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.424 | TFLOPs: 19.32 | +31: iteration 9890/ 39672 | consumed samples: 2531840 | consumed tokens: 5185208320 | elapsed time per iteration (s): 0.73 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 2.354099E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.071 | TFLOPs: 21.24 | +31: iteration 9900/ 39672 | consumed samples: 2534400 | consumed tokens: 5190451200 | elapsed time per iteration (s): 1.01 | learning rate: 1.752E-04 | global batch size: 256 | lm loss: 2.348507E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 254.354 | TFLOPs: 15.39 | +31: iteration 9910/ 39672 | consumed samples: 2536960 | consumed tokens: 5195694080 | elapsed time per iteration (s): 0.79 | learning rate: 1.752E-04 | global batch size: 256 | lm loss: 2.333269E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.554 | TFLOPs: 19.70 | +31: iteration 9920/ 39672 | consumed samples: 2539520 | consumed tokens: 5200936960 | elapsed time per iteration (s): 0.78 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 2.357894E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.848 | TFLOPs: 19.83 | +31: iteration 9930/ 39672 | consumed samples: 2542080 | consumed tokens: 5206179840 | elapsed time per iteration (s): 0.74 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 2.328642E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.799 | TFLOPs: 21.04 | +31: iteration 9940/ 39672 | consumed samples: 2544640 | consumed tokens: 5211422720 | elapsed time per iteration (s): 0.77 | learning rate: 1.750E-04 | global batch size: 256 | lm loss: 2.305970E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.426 | TFLOPs: 20.23 | +31: iteration 9950/ 39672 | consumed samples: 2547200 | consumed tokens: 5216665600 | elapsed time per iteration (s): 0.74 | learning rate: 1.750E-04 | global batch size: 256 | lm loss: 2.301859E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.348 | TFLOPs: 20.89 | +31: iteration 9960/ 39672 | consumed samples: 2549760 | consumed tokens: 5221908480 | elapsed time per iteration (s): 0.74 | learning rate: 1.749E-04 | global batch size: 256 | lm loss: 2.329814E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.889 | TFLOPs: 20.80 | +31: iteration 9970/ 39672 | consumed samples: 2552320 | consumed tokens: 5227151360 | elapsed time per iteration (s): 0.74 | learning rate: 1.749E-04 | global batch size: 256 | lm loss: 2.290820E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.301 | TFLOPs: 21.01 | +31: iteration 9980/ 39672 | consumed samples: 2554880 | consumed tokens: 5232394240 | elapsed time per iteration (s): 0.77 | learning rate: 1.748E-04 | global batch size: 256 | lm loss: 2.339045E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.105 | TFLOPs: 20.09 | +31: iteration 9990/ 39672 | consumed samples: 2557440 | consumed tokens: 5237637120 | elapsed time per iteration (s): 0.76 | learning rate: 1.748E-04 | global batch size: 256 | lm loss: 2.338067E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.153 | TFLOPs: 20.28 | + 0: [2022-11-30 11:26:48,282] [INFO] [logging.py:68:log_dist] [Rank 0] step=10000, skipped=0, lr=[0.00017472837931709298, 0.00017472837931709298, 0.00017472837931709298], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 10000/ 39672 | consumed samples: 2560000 | consumed tokens: 5242880000 | elapsed time per iteration (s): 0.80 | learning rate: 1.747E-04 | global batch size: 256 | lm loss: 2.345207E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.515 | TFLOPs: 19.39 | + 0: steps: 10000 loss: 2.3112 iter time (s): 0.777 samples/sec: 329.488 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 10000 | lm loss value: 2.257389E+00 | lm loss PPL: 9.558096E+00 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 10000 to checkpoints_1b121b + 0: [2022-11-30 11:26:48,562] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step10000 is begin to save! + 0: [2022-11-30 11:26:48,792] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_01-model_00-model_states.pt... + 0: [2022-11-30 11:26:49,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_01-model_00-model_states.pt. + 0: [2022-11-30 11:26:49,196] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_03-model_00-model_states.pt... + 0: [2022-11-30 11:26:49,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_03-model_00-model_states.pt. + 0: [2022-11-30 11:26:49,303] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_04-model_00-model_states.pt... + 0: [2022-11-30 11:26:49,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_04-model_00-model_states.pt. + 0: [2022-11-30 11:26:49,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_05-model_00-model_states.pt... + 0: [2022-11-30 11:26:49,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_05-model_00-model_states.pt. + 0: [2022-11-30 11:26:49,472] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_06-model_00-model_states.pt... + 0: [2022-11-30 11:26:49,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_06-model_00-model_states.pt. + 0: [2022-11-30 11:26:49,552] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_07-model_00-model_states.pt... + 0: [2022-11-30 11:26:49,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_07-model_00-model_states.pt. + 0: [2022-11-30 11:26:49,636] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_08-model_00-model_states.pt... + 0: [2022-11-30 11:26:49,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_08-model_00-model_states.pt. + 0: [2022-11-30 11:26:49,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_09-model_00-model_states.pt... + 0: [2022-11-30 11:26:49,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_09-model_00-model_states.pt. + 0: [2022-11-30 11:26:49,805] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_10-model_00-model_states.pt... + 0: [2022-11-30 11:26:49,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_10-model_00-model_states.pt. + 0: [2022-11-30 11:26:49,882] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_11-model_00-model_states.pt... + 0: [2022-11-30 11:26:49,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_11-model_00-model_states.pt. + 0: [2022-11-30 11:26:49,959] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_12-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_12-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,035] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_13-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_13-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,135] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_14-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_14-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,208] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_15-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_15-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,285] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_16-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_16-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,358] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_17-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_17-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,437] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_18-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_18-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,535] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_19-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_19-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,628] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_20-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_20-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_21-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_21-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,779] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_22-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_22-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,858] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_23-model_00-model_states.pt... + 0: [2022-11-30 11:26:50,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_23-model_00-model_states.pt. + 0: [2022-11-30 11:26:50,931] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_24-model_00-model_states.pt... + 0: [2022-11-30 11:26:51,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_24-model_00-model_states.pt. + 0: [2022-11-30 11:26:51,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_25-model_00-model_states.pt... + 0: [2022-11-30 11:26:51,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_25-model_00-model_states.pt. + 0: [2022-11-30 11:26:51,083] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_26-model_00-model_states.pt... + 0: [2022-11-30 11:26:51,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_26-model_00-model_states.pt. + 0: [2022-11-30 11:26:51,158] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_27-model_00-model_states.pt... + 0: [2022-11-30 11:26:51,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_27-model_00-model_states.pt. + 0: [2022-11-30 11:26:51,235] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_28-model_00-model_states.pt... + 0: [2022-11-30 11:26:51,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_28-model_00-model_states.pt. + 0: [2022-11-30 11:26:51,308] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/layer_30-model_00-model_states.pt... + 0: [2022-11-30 11:26:51,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/layer_30-model_00-model_states.pt. + 0: [2022-11-30 11:26:51,312] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_1b121b/global_step10000/mp_rank_00_model_states.pt + 0: [2022-11-30 11:26:51,312] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/mp_rank_00_model_states.pt... + 0: [2022-11-30 11:26:51,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/mp_rank_00_model_states.pt. + 0: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +29: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +20: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +22: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +14: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 0: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +19: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +12: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... + 8: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 3: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +23: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +21: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +29: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +24: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... + 5: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +13: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +30: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +10: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... + 6: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +27: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +31: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... + 7: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 9: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +11: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +20: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +17: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +22: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +26: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +16: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... + 1: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +15: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... + 2: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 4: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +14: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +18: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +28: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... + 0: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +19: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +12: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... + 8: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 3: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +23: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +21: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +29: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +24: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... + 5: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +13: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +30: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +10: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... + 6: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +27: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +31: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... + 7: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 9: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +11: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +20: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +17: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +22: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +26: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +16: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... + 1: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +15: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... + 2: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 4: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +14: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +18: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +28: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... + 0: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +19: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +12: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... + 8: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +23: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +21: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +29: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +24: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... + 5: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +30: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... + 6: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +27: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +25: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +31: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... + 7: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 9: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +11: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +20: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +22: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +26: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +16: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... + 1: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +15: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... + 2: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 4: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +14: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +18: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +28: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... + 0: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +19: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... + 8: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +23: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +29: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +24: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... + 6: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +27: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... + 7: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +11: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +20: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +22: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +15: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +14: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +18: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +19: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... + 8: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +23: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +29: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +27: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +11: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +22: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +15: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +14: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +18: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +23: [2022-11-30 11:26:51,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... + 0: [2022-11-30 11:26:51,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-30 11:26:51,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-30 11:26:51,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-30 11:26:51,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-30 11:26:51,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-30 11:26:51,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-30 11:26:51,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-30 11:26:51,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-30 11:26:51,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-30 11:26:51,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-30 11:26:51,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-30 11:26:51,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-30 11:26:51,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-30 11:26:51,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-30 11:26:51,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-30 11:26:51,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-30 11:26:51,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-30 11:26:51,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-30 11:26:51,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-30 11:26:51,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-30 11:26:51,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-30 11:26:51,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-30 11:26:51,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-30 11:26:51,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-30 11:26:51,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-30 11:26:51,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-30 11:26:51,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-30 11:26:51,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-30 11:26:51,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-30 11:26:51,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-30 11:26:51,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-30 11:26:51,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-30 11:26:51,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-30 11:26:51,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-30 11:26:51,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-30 11:26:51,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-30 11:26:51,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-30 11:26:51,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-30 11:26:51,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-30 11:26:51,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-30 11:26:51,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-30 11:26:51,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +18: [2022-11-30 11:26:51,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-30 11:26:51,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-30 11:26:51,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-30 11:26:51,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-30 11:26:51,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-30 11:26:51,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-30 11:26:51,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-30 11:26:51,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-30 11:26:51,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-30 11:26:51,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-30 11:26:51,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-30 11:26:51,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-30 11:26:51,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-30 11:26:51,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-30 11:26:51,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-30 11:26:51,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-30 11:26:51,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-30 11:26:51,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-30 11:26:51,520] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-30 11:26:51,520] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-30 11:26:51,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-30 11:26:51,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-30 11:26:51,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-30 11:26:51,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-30 11:26:51,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +12: [2022-11-30 11:26:51,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-30 11:26:51,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-30 11:26:51,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-30 11:26:51,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-30 11:26:51,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-30 11:26:51,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-30 11:26:51,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-30 11:26:51,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-30 11:26:51,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-30 11:26:51,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-30 11:26:51,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-30 11:26:51,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-30 11:26:51,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-30 11:26:51,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-30 11:26:51,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +26: [2022-11-30 11:26:51,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-30 11:26:51,525] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-30 11:26:51,525] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-30 11:26:51,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-30 11:26:51,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-30 11:26:51,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-30 11:26:51,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-30 11:26:51,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-30 11:26:51,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-30 11:26:51,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-30 11:26:51,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-30 11:26:51,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-30 11:26:51,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-30 11:26:51,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-30 11:26:51,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-30 11:26:51,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-30 11:26:51,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-30 11:26:51,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-30 11:26:51,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-30 11:26:51,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-30 11:26:51,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-30 11:26:51,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-30 11:26:51,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-30 11:26:51,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-30 11:26:51,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-30 11:26:51,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-30 11:26:51,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-30 11:26:51,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-30 11:26:51,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-30 11:26:51,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-30 11:26:51,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-30 11:26:51,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-30 11:26:51,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-30 11:26:51,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-30 11:26:51,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-30 11:26:51,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-30 11:26:51,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-30 11:26:51,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-30 11:26:51,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +20: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +20: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +25: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +20: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-30 11:26:51,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +25: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-30 11:26:51,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-30 11:26:51,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-30 11:26:51,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-30 11:26:51,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-30 11:26:51,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-30 11:26:51,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-30 11:26:51,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-30 11:26:51,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-30 11:26:51,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-30 11:26:51,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-30 11:26:51,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-30 11:26:51,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-30 11:26:51,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-30 11:26:51,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-30 11:26:51,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-30 11:26:51,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-30 11:26:51,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-30 11:26:51,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-30 11:26:51,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-30 11:26:51,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-30 11:26:51,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-30 11:26:51,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-30 11:26:51,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-30 11:26:51,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-30 11:26:51,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-30 11:26:51,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-30 11:26:51,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-30 11:26:51,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-30 11:26:51,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-30 11:26:51,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-30 11:26:51,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-30 11:26:51,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-30 11:26:51,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-30 11:26:51,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-30 11:26:51,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-30 11:26:51,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-30 11:26:51,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-30 11:26:51,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-30 11:26:51,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-30 11:26:51,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-30 11:26:51,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-30 11:26:51,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-30 11:26:51,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-30 11:26:51,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +26: [2022-11-30 11:26:51,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +10: [2022-11-30 11:26:51,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +26: [2022-11-30 11:26:51,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +10: [2022-11-30 11:26:51,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-30 11:26:51,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-30 11:26:51,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-30 11:26:51,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-30 11:26:51,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-30 11:26:51,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-30 11:26:51,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-30 11:26:51,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-30 11:26:51,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. + 8: [2022-11-30 11:26:51,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-30 11:26:51,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-30 11:26:51,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-30 11:26:51,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-30 11:26:51,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-30 11:26:51,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-30 11:26:51,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-30 11:26:51,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-30 11:26:51,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-30 11:26:51,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-30 11:26:51,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-30 11:26:51,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-30 11:26:51,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-30 11:26:51,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-30 11:26:51,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-30 11:26:51,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-30 11:26:51,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-30 11:26:51,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-30 11:26:51,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-30 11:26:51,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-30 11:26:51,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-30 11:26:51,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-30 11:26:51,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-30 11:26:51,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-30 11:26:51,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-30 11:26:51,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-30 11:26:51,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-30 11:26:51,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-30 11:26:51,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-30 11:26:51,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-30 11:26:51,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-30 11:26:51,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-30 11:26:51,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-30 11:26:51,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 5: [2022-11-30 11:26:51,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-30 11:26:51,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-30 11:26:51,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-30 11:26:51,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-30 11:26:51,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-30 11:26:51,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-30 11:26:51,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-30 11:26:51,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-30 11:26:51,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-30 11:26:51,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-30 11:26:51,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-30 11:26:51,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 5: [2022-11-30 11:26:51,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-30 11:26:51,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-30 11:26:51,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-30 11:26:51,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-30 11:26:51,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-30 11:26:51,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-30 11:26:51,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-30 11:26:51,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-30 11:26:51,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-30 11:26:51,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-30 11:26:51,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-30 11:26:51,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-30 11:26:51,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-30 11:26:51,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-30 11:26:51,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-30 11:26:51,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-30 11:26:51,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-30 11:26:51,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-30 11:26:51,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-30 11:26:51,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-30 11:26:51,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-30 11:26:51,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-30 11:26:51,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +12: [2022-11-30 11:26:51,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-30 11:26:51,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-30 11:26:51,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-30 11:26:51,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-30 11:26:51,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +15: [2022-11-30 11:26:51,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +27: [2022-11-30 11:26:51,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-30 11:26:51,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt + 3: [2022-11-30 11:26:51,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +15: [2022-11-30 11:26:51,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-30 11:26:51,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-30 11:26:51,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-30 11:26:51,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +28: [2022-11-30 11:26:51,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +10: [2022-11-30 11:26:51,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +28: [2022-11-30 11:26:51,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-30 11:26:51,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-30 11:26:51,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-30 11:26:51,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-30 11:26:51,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-30 11:26:51,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-30 11:26:51,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-30 11:26:51,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-30 11:26:51,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-30 11:26:51,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-30 11:26:51,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-30 11:26:51,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-30 11:26:51,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-30 11:26:51,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-30 11:26:51,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-30 11:26:51,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-30 11:26:51,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-30 11:26:51,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-30 11:26:51,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-30 11:26:51,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-30 11:26:51,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-30 11:26:51,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-30 11:26:51,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-30 11:26:51,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-30 11:26:51,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-30 11:26:51,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 1: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 9: [2022-11-30 11:26:51,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-30 11:26:51,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-30 11:26:51,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-30 11:26:51,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-30 11:26:51,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-30 11:26:51,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 9: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-30 11:26:51,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-30 11:26:51,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-30 11:26:51,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-30 11:26:51,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-30 11:26:51,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-30 11:26:51,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-30 11:26:51,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-30 11:26:51,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-30 11:26:51,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-30 11:26:51,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-30 11:26:51,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-30 11:26:51,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-30 11:26:51,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-30 11:26:51,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-30 11:26:51,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-30 11:26:51,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-30 11:26:51,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-30 11:26:51,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-30 11:26:51,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-30 11:26:51,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-30 11:26:51,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-30 11:26:51,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-30 11:26:51,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-30 11:26:51,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-30 11:26:51,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-30 11:26:51,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 7: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 6: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-30 11:26:51,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-30 11:26:51,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-30 11:26:51,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-30 11:26:51,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-30 11:26:51,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-30 11:26:51,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-30 11:26:51,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +20: [2022-11-30 11:26:51,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-30 11:26:51,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-30 11:26:51,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-30 11:26:51,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-30 11:26:51,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-30 11:26:51,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-30 11:26:51,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-30 11:26:51,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-30 11:26:51,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-30 11:26:51,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-30 11:26:51,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-30 11:26:51,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-30 11:26:51,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-30 11:26:51,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-30 11:26:51,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-30 11:26:51,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-30 11:26:51,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-30 11:26:51,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-30 11:26:51,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-30 11:26:51,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-30 11:26:51,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-30 11:26:51,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-30 11:26:51,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-30 11:26:51,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-30 11:26:51,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-30 11:26:51,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-30 11:26:51,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-30 11:26:51,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +29: [2022-11-30 11:26:51,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-30 11:26:51,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-30 11:26:51,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-30 11:26:51,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-30 11:26:51,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-30 11:26:51,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-30 11:26:51,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-30 11:26:51,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-30 11:26:51,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-30 11:26:51,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-30 11:26:51,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-30 11:26:51,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-30 11:26:51,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-30 11:26:51,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +17: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. + 8: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +17: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +24: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +18: [2022-11-30 11:26:51,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-30 11:26:51,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +24: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +18: [2022-11-30 11:26:51,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-30 11:26:51,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +18: [2022-11-30 11:26:51,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +22: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +18: [2022-11-30 11:26:51,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt + 3: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +22: [2022-11-30 11:26:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +18: [2022-11-30 11:26:51,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-30 11:26:51,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-30 11:26:51,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-30 11:26:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-30 11:26:51,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-30 11:26:51,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-30 11:26:51,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-30 11:26:51,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-30 11:26:51,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +26: [2022-11-30 11:26:51,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +17: [2022-11-30 11:26:51,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-30 11:26:51,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-30 11:26:51,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-30 11:26:51,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-30 11:26:51,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-30 11:26:51,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-30 11:26:51,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-30 11:26:51,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-30 11:26:51,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-30 11:26:51,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-30 11:26:51,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-30 11:26:51,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-30 11:26:51,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-30 11:26:51,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-30 11:26:51,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-30 11:26:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-30 11:26:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-30 11:26:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-30 11:26:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-30 11:26:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-30 11:26:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-30 11:26:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-30 11:26:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-30 11:26:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-30 11:26:51,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-30 11:26:51,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-30 11:26:51,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-30 11:26:51,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-30 11:26:51,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-30 11:26:51,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-30 11:26:51,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-30 11:26:51,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-30 11:26:51,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. + 0: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +10: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. + 0: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +10: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +21: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +19: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +21: [2022-11-30 11:26:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +19: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-30 11:26:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-30 11:26:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-30 11:26:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-30 11:26:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-30 11:26:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-30 11:26:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-30 11:26:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-30 11:26:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-30 11:26:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-30 11:26:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-30 11:26:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-30 11:26:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-30 11:26:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-30 11:26:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-30 11:26:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-30 11:26:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-30 11:26:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-30 11:26:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-30 11:26:51,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-30 11:26:51,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-30 11:26:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. + 7: [2022-11-30 11:26:51,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +20: [2022-11-30 11:26:51,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt + 7: [2022-11-30 11:26:51,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +20: [2022-11-30 11:26:51,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-30 11:26:51,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-30 11:26:51,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-30 11:26:51,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-30 11:26:51,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-30 11:26:51,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-30 11:26:51,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-30 11:26:51,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-30 11:26:51,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-30 11:26:51,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-30 11:26:51,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-30 11:26:51,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-30 11:26:51,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-30 11:26:51,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-30 11:26:51,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-30 11:26:51,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-30 11:26:51,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-30 11:26:51,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-30 11:26:51,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-30 11:26:51,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-30 11:26:51,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-30 11:26:51,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-30 11:26:51,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-30 11:26:51,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-30 11:26:51,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-30 11:26:51,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-30 11:26:51,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-30 11:26:51,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-30 11:26:51,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-30 11:26:51,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-30 11:26:51,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-30 11:26:51,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-30 11:26:51,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-30 11:26:51,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-30 11:26:51,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-30 11:26:51,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-30 11:26:51,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-30 11:26:51,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-30 11:26:51,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-30 11:26:51,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-30 11:26:51,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-30 11:26:51,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +21: [2022-11-30 11:26:51,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +17: [2022-11-30 11:26:51,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +21: [2022-11-30 11:26:51,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +17: [2022-11-30 11:26:51,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-30 11:26:51,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-30 11:26:51,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-30 11:26:51,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-30 11:26:51,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-30 11:26:51,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +31: [2022-11-30 11:26:51,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-30 11:26:51,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-30 11:26:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-30 11:26:51,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-30 11:26:51,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-30 11:26:51,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-30 11:26:51,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-30 11:26:51,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-30 11:26:51,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-30 11:26:51,646] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-30 11:26:51,646] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: successfully saved checkpoint at iteration 10000 to checkpoints_1b121b +31: time (ms) | save-checkpoint: 3116.60 +31: iteration 10010/ 39672 | consumed samples: 2562560 | consumed tokens: 5248122880 | elapsed time per iteration (s): 1.05 | learning rate: 1.747E-04 | global batch size: 256 | lm loss: 2.314298E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 243.039 | TFLOPs: 14.70 | +31: iteration 10020/ 39672 | consumed samples: 2565120 | consumed tokens: 5253365760 | elapsed time per iteration (s): 0.77 | learning rate: 1.746E-04 | global batch size: 256 | lm loss: 2.340038E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.152 | TFLOPs: 20.15 | +31: iteration 10030/ 39672 | consumed samples: 2567680 | consumed tokens: 5258608640 | elapsed time per iteration (s): 0.79 | learning rate: 1.746E-04 | global batch size: 256 | lm loss: 2.341102E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.644 | TFLOPs: 19.52 | +31: iteration 10040/ 39672 | consumed samples: 2570240 | consumed tokens: 5263851520 | elapsed time per iteration (s): 0.81 | learning rate: 1.745E-04 | global batch size: 256 | lm loss: 2.340273E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.145 | TFLOPs: 19.19 | +31: iteration 10050/ 39672 | consumed samples: 2572800 | consumed tokens: 5269094400 | elapsed time per iteration (s): 0.84 | learning rate: 1.745E-04 | global batch size: 256 | lm loss: 2.319283E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.919 | TFLOPs: 18.51 | +31: iteration 10060/ 39672 | consumed samples: 2575360 | consumed tokens: 5274337280 | elapsed time per iteration (s): 0.84 | learning rate: 1.744E-04 | global batch size: 256 | lm loss: 2.322815E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.421 | TFLOPs: 18.48 | +31: iteration 10070/ 39672 | consumed samples: 2577920 | consumed tokens: 5279580160 | elapsed time per iteration (s): 0.84 | learning rate: 1.744E-04 | global batch size: 256 | lm loss: 2.322611E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.675 | TFLOPs: 18.49 | +31: iteration 10080/ 39672 | consumed samples: 2580480 | consumed tokens: 5284823040 | elapsed time per iteration (s): 0.79 | learning rate: 1.743E-04 | global batch size: 256 | lm loss: 2.288282E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.201 | TFLOPs: 19.61 | +31: iteration 10090/ 39672 | consumed samples: 2583040 | consumed tokens: 5290065920 | elapsed time per iteration (s): 0.84 | learning rate: 1.743E-04 | global batch size: 256 | lm loss: 2.300490E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.336 | TFLOPs: 18.41 | +31: iteration 10100/ 39672 | consumed samples: 2585600 | consumed tokens: 5295308800 | elapsed time per iteration (s): 0.83 | learning rate: 1.742E-04 | global batch size: 256 | lm loss: 2.328890E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.815 | TFLOPs: 18.56 | +31: iteration 10110/ 39672 | consumed samples: 2588160 | consumed tokens: 5300551680 | elapsed time per iteration (s): 0.81 | learning rate: 1.742E-04 | global batch size: 256 | lm loss: 2.303555E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.683 | TFLOPs: 19.10 | +31: iteration 10120/ 39672 | consumed samples: 2590720 | consumed tokens: 5305794560 | elapsed time per iteration (s): 0.81 | learning rate: 1.741E-04 | global batch size: 256 | lm loss: 2.291362E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.692 | TFLOPs: 19.10 | +31: iteration 10130/ 39672 | consumed samples: 2593280 | consumed tokens: 5311037440 | elapsed time per iteration (s): 0.79 | learning rate: 1.741E-04 | global batch size: 256 | lm loss: 2.314722E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.316 | TFLOPs: 19.50 | +31: iteration 10140/ 39672 | consumed samples: 2595840 | consumed tokens: 5316280320 | elapsed time per iteration (s): 0.80 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 2.327802E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.189 | TFLOPs: 19.25 | +31: iteration 10150/ 39672 | consumed samples: 2598400 | consumed tokens: 5321523200 | elapsed time per iteration (s): 0.81 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 2.295200E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.753 | TFLOPs: 19.10 | +31: iteration 10160/ 39672 | consumed samples: 2600960 | consumed tokens: 5326766080 | elapsed time per iteration (s): 0.81 | learning rate: 1.739E-04 | global batch size: 256 | lm loss: 2.316145E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.423 | TFLOPs: 19.20 | +31: iteration 10170/ 39672 | consumed samples: 2603520 | consumed tokens: 5332008960 | elapsed time per iteration (s): 0.79 | learning rate: 1.739E-04 | global batch size: 256 | lm loss: 2.336832E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.936 | TFLOPs: 19.72 | +31: iteration 10180/ 39672 | consumed samples: 2606080 | consumed tokens: 5337251840 | elapsed time per iteration (s): 0.80 | learning rate: 1.738E-04 | global batch size: 256 | lm loss: 2.309138E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.967 | TFLOPs: 19.42 | +31: iteration 10190/ 39672 | consumed samples: 2608640 | consumed tokens: 5342494720 | elapsed time per iteration (s): 0.80 | learning rate: 1.738E-04 | global batch size: 256 | lm loss: 2.323150E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.239 | TFLOPs: 19.25 | +31: iteration 10200/ 39672 | consumed samples: 2611200 | consumed tokens: 5347737600 | elapsed time per iteration (s): 0.74 | learning rate: 1.737E-04 | global batch size: 256 | lm loss: 2.309166E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.668 | TFLOPs: 20.79 | +31: iteration 10210/ 39672 | consumed samples: 2613760 | consumed tokens: 5352980480 | elapsed time per iteration (s): 0.79 | learning rate: 1.737E-04 | global batch size: 256 | lm loss: 2.312730E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.160 | TFLOPs: 19.61 | +31: iteration 10220/ 39672 | consumed samples: 2616320 | consumed tokens: 5358223360 | elapsed time per iteration (s): 0.75 | learning rate: 1.736E-04 | global batch size: 256 | lm loss: 2.292598E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.573 | TFLOPs: 20.79 | +31: iteration 10230/ 39672 | consumed samples: 2618880 | consumed tokens: 5363466240 | elapsed time per iteration (s): 0.74 | learning rate: 1.736E-04 | global batch size: 256 | lm loss: 2.308949E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.290 | TFLOPs: 21.01 | +31: iteration 10240/ 39672 | consumed samples: 2621440 | consumed tokens: 5368709120 | elapsed time per iteration (s): 0.76 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 2.327147E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.732 | TFLOPs: 20.37 | +31: iteration 10250/ 39672 | consumed samples: 2624000 | consumed tokens: 5373952000 | elapsed time per iteration (s): 0.72 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 2.318399E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.658 | TFLOPs: 21.40 | +31: iteration 10260/ 39672 | consumed samples: 2626560 | consumed tokens: 5379194880 | elapsed time per iteration (s): 0.78 | learning rate: 1.734E-04 | global batch size: 256 | lm loss: 2.291004E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.548 | TFLOPs: 19.76 | +31: iteration 10270/ 39672 | consumed samples: 2629120 | consumed tokens: 5384437760 | elapsed time per iteration (s): 0.77 | learning rate: 1.734E-04 | global batch size: 256 | lm loss: 2.314141E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.010 | TFLOPs: 20.21 | +31: iteration 10280/ 39672 | consumed samples: 2631680 | consumed tokens: 5389680640 | elapsed time per iteration (s): 0.77 | learning rate: 1.733E-04 | global batch size: 256 | lm loss: 2.321865E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.161 | TFLOPs: 20.16 | +31: iteration 10290/ 39672 | consumed samples: 2634240 | consumed tokens: 5394923520 | elapsed time per iteration (s): 0.84 | learning rate: 1.733E-04 | global batch size: 256 | lm loss: 2.335388E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.098 | TFLOPs: 18.52 | +31: iteration 10300/ 39672 | consumed samples: 2636800 | consumed tokens: 5400166400 | elapsed time per iteration (s): 0.77 | learning rate: 1.732E-04 | global batch size: 256 | lm loss: 2.289820E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.925 | TFLOPs: 20.20 | +31: iteration 10310/ 39672 | consumed samples: 2639360 | consumed tokens: 5405409280 | elapsed time per iteration (s): 0.76 | learning rate: 1.732E-04 | global batch size: 256 | lm loss: 2.319790E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.751 | TFLOPs: 20.49 | +31: iteration 10320/ 39672 | consumed samples: 2641920 | consumed tokens: 5410652160 | elapsed time per iteration (s): 0.74 | learning rate: 1.731E-04 | global batch size: 256 | lm loss: 2.339052E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.726 | TFLOPs: 20.79 | +31: iteration 10330/ 39672 | consumed samples: 2644480 | consumed tokens: 5415895040 | elapsed time per iteration (s): 0.73 | learning rate: 1.731E-04 | global batch size: 256 | lm loss: 2.297754E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.026 | TFLOPs: 21.30 | +31: iteration 10340/ 39672 | consumed samples: 2647040 | consumed tokens: 5421137920 | elapsed time per iteration (s): 0.75 | learning rate: 1.730E-04 | global batch size: 256 | lm loss: 2.340337E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.071 | TFLOPs: 20.57 | +31: iteration 10350/ 39672 | consumed samples: 2649600 | consumed tokens: 5426380800 | elapsed time per iteration (s): 0.80 | learning rate: 1.730E-04 | global batch size: 256 | lm loss: 2.313138E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.422 | TFLOPs: 19.32 | +31: iteration 10360/ 39672 | consumed samples: 2652160 | consumed tokens: 5431623680 | elapsed time per iteration (s): 0.79 | learning rate: 1.729E-04 | global batch size: 256 | lm loss: 2.318693E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.838 | TFLOPs: 19.71 | +31: iteration 10370/ 39672 | consumed samples: 2654720 | consumed tokens: 5436866560 | elapsed time per iteration (s): 0.74 | learning rate: 1.728E-04 | global batch size: 256 | lm loss: 2.313038E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.662 | TFLOPs: 20.91 | +31: iteration 10380/ 39672 | consumed samples: 2657280 | consumed tokens: 5442109440 | elapsed time per iteration (s): 0.77 | learning rate: 1.728E-04 | global batch size: 256 | lm loss: 2.308626E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.161 | TFLOPs: 20.16 | +31: iteration 10390/ 39672 | consumed samples: 2659840 | consumed tokens: 5447352320 | elapsed time per iteration (s): 0.76 | learning rate: 1.727E-04 | global batch size: 256 | lm loss: 2.297101E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.221 | TFLOPs: 20.28 | +31: iteration 10400/ 39672 | consumed samples: 2662400 | consumed tokens: 5452595200 | elapsed time per iteration (s): 0.72 | learning rate: 1.727E-04 | global batch size: 256 | lm loss: 2.309103E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.999 | TFLOPs: 21.66 | +31: iteration 10410/ 39672 | consumed samples: 2664960 | consumed tokens: 5457838080 | elapsed time per iteration (s): 0.78 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 2.301337E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.642 | TFLOPs: 19.94 | +31: iteration 10420/ 39672 | consumed samples: 2667520 | consumed tokens: 5463080960 | elapsed time per iteration (s): 0.78 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 2.323578E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.366 | TFLOPs: 19.87 | +31: iteration 10430/ 39672 | consumed samples: 2670080 | consumed tokens: 5468323840 | elapsed time per iteration (s): 0.75 | learning rate: 1.725E-04 | global batch size: 256 | lm loss: 2.319301E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.677 | TFLOPs: 20.73 | +31: iteration 10440/ 39672 | consumed samples: 2672640 | consumed tokens: 5473566720 | elapsed time per iteration (s): 0.77 | learning rate: 1.725E-04 | global batch size: 256 | lm loss: 2.309679E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.895 | TFLOPs: 20.14 | +31: iteration 10450/ 39672 | consumed samples: 2675200 | consumed tokens: 5478809600 | elapsed time per iteration (s): 0.78 | learning rate: 1.724E-04 | global batch size: 256 | lm loss: 2.296704E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.419 | TFLOPs: 19.81 | +31: iteration 10460/ 39672 | consumed samples: 2677760 | consumed tokens: 5484052480 | elapsed time per iteration (s): 0.79 | learning rate: 1.724E-04 | global batch size: 256 | lm loss: 2.304183E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.388 | TFLOPs: 19.56 | +31: iteration 10470/ 39672 | consumed samples: 2680320 | consumed tokens: 5489295360 | elapsed time per iteration (s): 0.75 | learning rate: 1.723E-04 | global batch size: 256 | lm loss: 2.308091E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.254 | TFLOPs: 20.65 | +31: iteration 10480/ 39672 | consumed samples: 2682880 | consumed tokens: 5494538240 | elapsed time per iteration (s): 0.75 | learning rate: 1.723E-04 | global batch size: 256 | lm loss: 2.637094E+00 | grad norm: 6.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.020 | TFLOPs: 20.69 | +31: iteration 10490/ 39672 | consumed samples: 2685440 | consumed tokens: 5499781120 | elapsed time per iteration (s): 0.78 | learning rate: 1.722E-04 | global batch size: 256 | lm loss: 2.460490E+00 | grad norm: 0.485 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.219 | TFLOPs: 19.98 | +31: iteration 10500/ 39672 | consumed samples: 2688000 | consumed tokens: 5505024000 | elapsed time per iteration (s): 0.75 | learning rate: 1.722E-04 | global batch size: 256 | lm loss: 2.351158E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.626 | TFLOPs: 20.67 | +31: iteration 10510/ 39672 | consumed samples: 2690560 | consumed tokens: 5510266880 | elapsed time per iteration (s): 0.82 | learning rate: 1.721E-04 | global batch size: 256 | lm loss: 2.345910E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.036 | TFLOPs: 18.94 | +31: iteration 10520/ 39672 | consumed samples: 2693120 | consumed tokens: 5515509760 | elapsed time per iteration (s): 0.78 | learning rate: 1.721E-04 | global batch size: 256 | lm loss: 2.367896E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.598 | TFLOPs: 19.76 | +31: iteration 10530/ 39672 | consumed samples: 2695680 | consumed tokens: 5520752640 | elapsed time per iteration (s): 0.81 | learning rate: 1.720E-04 | global batch size: 256 | lm loss: 2.320522E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.576 | TFLOPs: 19.15 | +31: iteration 10540/ 39672 | consumed samples: 2698240 | consumed tokens: 5525995520 | elapsed time per iteration (s): 0.80 | learning rate: 1.720E-04 | global batch size: 256 | lm loss: 2.309961E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.306 | TFLOPs: 19.44 | +31: iteration 10550/ 39672 | consumed samples: 2700800 | consumed tokens: 5531238400 | elapsed time per iteration (s): 0.82 | learning rate: 1.719E-04 | global batch size: 256 | lm loss: 2.298279E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.391 | TFLOPs: 18.90 | +31: iteration 10560/ 39672 | consumed samples: 2703360 | consumed tokens: 5536481280 | elapsed time per iteration (s): 0.73 | learning rate: 1.719E-04 | global batch size: 256 | lm loss: 2.304495E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.797 | TFLOPs: 21.22 | +31: iteration 10570/ 39672 | consumed samples: 2705920 | consumed tokens: 5541724160 | elapsed time per iteration (s): 0.76 | learning rate: 1.718E-04 | global batch size: 256 | lm loss: 2.301701E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.941 | TFLOPs: 20.51 | +31: iteration 10580/ 39672 | consumed samples: 2708480 | consumed tokens: 5546967040 | elapsed time per iteration (s): 0.76 | learning rate: 1.718E-04 | global batch size: 256 | lm loss: 2.306036E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.515 | TFLOPs: 20.30 | +31: iteration 10590/ 39672 | consumed samples: 2711040 | consumed tokens: 5552209920 | elapsed time per iteration (s): 0.75 | learning rate: 1.717E-04 | global batch size: 256 | lm loss: 2.337453E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.701 | TFLOPs: 20.67 | +31: iteration 10600/ 39672 | consumed samples: 2713600 | consumed tokens: 5557452800 | elapsed time per iteration (s): 0.77 | learning rate: 1.717E-04 | global batch size: 256 | lm loss: 2.301486E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.246 | TFLOPs: 20.10 | +31: iteration 10610/ 39672 | consumed samples: 2716160 | consumed tokens: 5562695680 | elapsed time per iteration (s): 0.81 | learning rate: 1.716E-04 | global batch size: 256 | lm loss: 2.282769E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.318 | TFLOPs: 19.20 | +31: iteration 10620/ 39672 | consumed samples: 2718720 | consumed tokens: 5567938560 | elapsed time per iteration (s): 0.81 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 2.296814E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.188 | TFLOPs: 19.19 | +31: iteration 10630/ 39672 | consumed samples: 2721280 | consumed tokens: 5573181440 | elapsed time per iteration (s): 0.73 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 2.281030E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.723 | TFLOPs: 21.16 | +31: iteration 10640/ 39672 | consumed samples: 2723840 | consumed tokens: 5578424320 | elapsed time per iteration (s): 0.78 | learning rate: 1.714E-04 | global batch size: 256 | lm loss: 2.310922E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.662 | TFLOPs: 19.94 | +31: iteration 10650/ 39672 | consumed samples: 2726400 | consumed tokens: 5583667200 | elapsed time per iteration (s): 0.77 | learning rate: 1.714E-04 | global batch size: 256 | lm loss: 2.316208E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.740 | TFLOPs: 20.07 | +31: iteration 10660/ 39672 | consumed samples: 2728960 | consumed tokens: 5588910080 | elapsed time per iteration (s): 0.82 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 2.308758E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.633 | TFLOPs: 18.97 | +31: iteration 10670/ 39672 | consumed samples: 2731520 | consumed tokens: 5594152960 | elapsed time per iteration (s): 0.78 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 2.327642E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.420 | TFLOPs: 19.93 | +31: iteration 10680/ 39672 | consumed samples: 2734080 | consumed tokens: 5599395840 | elapsed time per iteration (s): 0.88 | learning rate: 1.712E-04 | global batch size: 256 | lm loss: 2.301655E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 292.080 | TFLOPs: 17.67 | +31: iteration 10690/ 39672 | consumed samples: 2736640 | consumed tokens: 5604638720 | elapsed time per iteration (s): 0.83 | learning rate: 1.712E-04 | global batch size: 256 | lm loss: 2.319206E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.872 | TFLOPs: 18.57 | +31: iteration 10700/ 39672 | consumed samples: 2739200 | consumed tokens: 5609881600 | elapsed time per iteration (s): 0.80 | learning rate: 1.711E-04 | global batch size: 256 | lm loss: 2.302684E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.712 | TFLOPs: 19.28 | +31: iteration 10710/ 39672 | consumed samples: 2741760 | consumed tokens: 5615124480 | elapsed time per iteration (s): 0.75 | learning rate: 1.711E-04 | global batch size: 256 | lm loss: 2.324119E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.937 | TFLOPs: 20.57 | +31: iteration 10720/ 39672 | consumed samples: 2744320 | consumed tokens: 5620367360 | elapsed time per iteration (s): 0.78 | learning rate: 1.710E-04 | global batch size: 256 | lm loss: 2.332450E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.445 | TFLOPs: 19.87 | +31: iteration 10730/ 39672 | consumed samples: 2746880 | consumed tokens: 5625610240 | elapsed time per iteration (s): 0.73 | learning rate: 1.710E-04 | global batch size: 256 | lm loss: 2.303044E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.672 | TFLOPs: 21.09 | +31: iteration 10740/ 39672 | consumed samples: 2749440 | consumed tokens: 5630853120 | elapsed time per iteration (s): 0.77 | learning rate: 1.709E-04 | global batch size: 256 | lm loss: 2.288063E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.680 | TFLOPs: 20.19 | +31: iteration 10750/ 39672 | consumed samples: 2752000 | consumed tokens: 5636096000 | elapsed time per iteration (s): 0.80 | learning rate: 1.709E-04 | global batch size: 256 | lm loss: 2.323325E+00 | grad norm: 1.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.509 | TFLOPs: 19.27 | +31: iteration 10760/ 39672 | consumed samples: 2754560 | consumed tokens: 5641338880 | elapsed time per iteration (s): 0.75 | learning rate: 1.708E-04 | global batch size: 256 | lm loss: 2.409220E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.915 | TFLOPs: 20.75 | +31: iteration 10770/ 39672 | consumed samples: 2757120 | consumed tokens: 5646581760 | elapsed time per iteration (s): 0.79 | learning rate: 1.708E-04 | global batch size: 256 | lm loss: 2.316050E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.974 | TFLOPs: 19.72 | +31: iteration 10780/ 39672 | consumed samples: 2759680 | consumed tokens: 5651824640 | elapsed time per iteration (s): 0.77 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 2.292109E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.200 | TFLOPs: 20.04 | +31: iteration 10790/ 39672 | consumed samples: 2762240 | consumed tokens: 5657067520 | elapsed time per iteration (s): 0.79 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 2.328044E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.155 | TFLOPs: 19.61 | +31: iteration 10800/ 39672 | consumed samples: 2764800 | consumed tokens: 5662310400 | elapsed time per iteration (s): 0.82 | learning rate: 1.706E-04 | global batch size: 256 | lm loss: 2.287030E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.698 | TFLOPs: 18.86 | +31: iteration 10810/ 39672 | consumed samples: 2767360 | consumed tokens: 5667553280 | elapsed time per iteration (s): 0.82 | learning rate: 1.705E-04 | global batch size: 256 | lm loss: 2.294348E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.646 | TFLOPs: 18.79 | +31: iteration 10820/ 39672 | consumed samples: 2769920 | consumed tokens: 5672796160 | elapsed time per iteration (s): 0.84 | learning rate: 1.705E-04 | global batch size: 256 | lm loss: 2.299986E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.859 | TFLOPs: 18.44 | +31: iteration 10830/ 39672 | consumed samples: 2772480 | consumed tokens: 5678039040 | elapsed time per iteration (s): 0.80 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 2.304801E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.598 | TFLOPs: 19.33 | +31: iteration 10840/ 39672 | consumed samples: 2775040 | consumed tokens: 5683281920 | elapsed time per iteration (s): 0.85 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 2.299036E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.442 | TFLOPs: 18.30 | +31: iteration 10850/ 39672 | consumed samples: 2777600 | consumed tokens: 5688524800 | elapsed time per iteration (s): 0.85 | learning rate: 1.703E-04 | global batch size: 256 | lm loss: 2.266237E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.515 | TFLOPs: 18.24 | +31: iteration 10860/ 39672 | consumed samples: 2780160 | consumed tokens: 5693767680 | elapsed time per iteration (s): 0.86 | learning rate: 1.703E-04 | global batch size: 256 | lm loss: 2.326936E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.126 | TFLOPs: 17.98 | +31: iteration 10870/ 39672 | consumed samples: 2782720 | consumed tokens: 5699010560 | elapsed time per iteration (s): 0.81 | learning rate: 1.702E-04 | global batch size: 256 | lm loss: 2.306619E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.898 | TFLOPs: 19.17 | +31: iteration 10880/ 39672 | consumed samples: 2785280 | consumed tokens: 5704253440 | elapsed time per iteration (s): 0.79 | learning rate: 1.702E-04 | global batch size: 256 | lm loss: 2.317508E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.204 | TFLOPs: 19.55 | +31: iteration 10890/ 39672 | consumed samples: 2787840 | consumed tokens: 5709496320 | elapsed time per iteration (s): 0.80 | learning rate: 1.701E-04 | global batch size: 256 | lm loss: 2.299246E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.616 | TFLOPs: 19.28 | +31: iteration 10900/ 39672 | consumed samples: 2790400 | consumed tokens: 5714739200 | elapsed time per iteration (s): 0.83 | learning rate: 1.701E-04 | global batch size: 256 | lm loss: 2.292374E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.259 | TFLOPs: 18.77 | +31: iteration 10910/ 39672 | consumed samples: 2792960 | consumed tokens: 5719982080 | elapsed time per iteration (s): 0.85 | learning rate: 1.700E-04 | global batch size: 256 | lm loss: 2.325403E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.712 | TFLOPs: 18.31 | +31: iteration 10920/ 39672 | consumed samples: 2795520 | consumed tokens: 5725224960 | elapsed time per iteration (s): 0.89 | learning rate: 1.700E-04 | global batch size: 256 | lm loss: 2.276208E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 287.036 | TFLOPs: 17.36 | +31: iteration 10930/ 39672 | consumed samples: 2798080 | consumed tokens: 5730467840 | elapsed time per iteration (s): 0.78 | learning rate: 1.699E-04 | global batch size: 256 | lm loss: 2.284520E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.515 | TFLOPs: 19.87 | +31: iteration 10940/ 39672 | consumed samples: 2800640 | consumed tokens: 5735710720 | elapsed time per iteration (s): 0.80 | learning rate: 1.698E-04 | global batch size: 256 | lm loss: 2.258110E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.953 | TFLOPs: 19.30 | +31: iteration 10950/ 39672 | consumed samples: 2803200 | consumed tokens: 5740953600 | elapsed time per iteration (s): 0.85 | learning rate: 1.698E-04 | global batch size: 256 | lm loss: 2.317889E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.164 | TFLOPs: 18.16 | +31: iteration 10960/ 39672 | consumed samples: 2805760 | consumed tokens: 5746196480 | elapsed time per iteration (s): 0.79 | learning rate: 1.697E-04 | global batch size: 256 | lm loss: 2.289354E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.330 | TFLOPs: 19.68 | +31: iteration 10970/ 39672 | consumed samples: 2808320 | consumed tokens: 5751439360 | elapsed time per iteration (s): 0.82 | learning rate: 1.697E-04 | global batch size: 256 | lm loss: 2.295256E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.057 | TFLOPs: 18.82 | +31: iteration 10980/ 39672 | consumed samples: 2810880 | consumed tokens: 5756682240 | elapsed time per iteration (s): 0.83 | learning rate: 1.696E-04 | global batch size: 256 | lm loss: 2.291945E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.382 | TFLOPs: 18.60 | +31: iteration 10990/ 39672 | consumed samples: 2813440 | consumed tokens: 5761925120 | elapsed time per iteration (s): 0.78 | learning rate: 1.696E-04 | global batch size: 256 | lm loss: 2.303087E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.253 | TFLOPs: 19.80 | +31: iteration 11000/ 39672 | consumed samples: 2816000 | consumed tokens: 5767168000 | elapsed time per iteration (s): 0.86 | learning rate: 1.695E-04 | global batch size: 256 | lm loss: 2.302288E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.880 | TFLOPs: 17.96 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 11000 | lm loss value: 2.232174E+00 | lm loss PPL: 9.320110E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 11010/ 39672 | consumed samples: 2818560 | consumed tokens: 5772410880 | elapsed time per iteration (s): 0.85 | learning rate: 1.695E-04 | global batch size: 256 | lm loss: 2.279278E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.739 | TFLOPs: 18.31 | +31: iteration 11020/ 39672 | consumed samples: 2821120 | consumed tokens: 5777653760 | elapsed time per iteration (s): 0.82 | learning rate: 1.694E-04 | global batch size: 256 | lm loss: 2.326915E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.122 | TFLOPs: 18.88 | +31: iteration 11030/ 39672 | consumed samples: 2823680 | consumed tokens: 5782896640 | elapsed time per iteration (s): 0.84 | learning rate: 1.694E-04 | global batch size: 256 | lm loss: 2.268586E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.492 | TFLOPs: 18.48 | +31: iteration 11040/ 39672 | consumed samples: 2826240 | consumed tokens: 5788139520 | elapsed time per iteration (s): 0.80 | learning rate: 1.693E-04 | global batch size: 256 | lm loss: 2.294682E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.272 | TFLOPs: 19.44 | +31: iteration 11050/ 39672 | consumed samples: 2828800 | consumed tokens: 5793382400 | elapsed time per iteration (s): 0.80 | learning rate: 1.693E-04 | global batch size: 256 | lm loss: 2.311502E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.037 | TFLOPs: 19.24 | +31: iteration 11060/ 39672 | consumed samples: 2831360 | consumed tokens: 5798625280 | elapsed time per iteration (s): 0.77 | learning rate: 1.692E-04 | global batch size: 256 | lm loss: 2.275562E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.479 | TFLOPs: 20.24 | +31: iteration 11070/ 39672 | consumed samples: 2833920 | consumed tokens: 5803868160 | elapsed time per iteration (s): 0.76 | learning rate: 1.691E-04 | global batch size: 256 | lm loss: 2.284302E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.277 | TFLOPs: 20.40 | +31: iteration 11080/ 39672 | consumed samples: 2836480 | consumed tokens: 5809111040 | elapsed time per iteration (s): 0.73 | learning rate: 1.691E-04 | global batch size: 256 | lm loss: 2.304480E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.268 | TFLOPs: 21.19 | +31: iteration 11090/ 39672 | consumed samples: 2839040 | consumed tokens: 5814353920 | elapsed time per iteration (s): 0.75 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 2.286868E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.961 | TFLOPs: 20.75 | +31: iteration 11100/ 39672 | consumed samples: 2841600 | consumed tokens: 5819596800 | elapsed time per iteration (s): 0.74 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 2.312635E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.963 | TFLOPs: 20.81 | +31: iteration 11110/ 39672 | consumed samples: 2844160 | consumed tokens: 5824839680 | elapsed time per iteration (s): 0.79 | learning rate: 1.689E-04 | global batch size: 256 | lm loss: 2.321734E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.180 | TFLOPs: 19.61 | +31: iteration 11120/ 39672 | consumed samples: 2846720 | consumed tokens: 5830082560 | elapsed time per iteration (s): 0.75 | learning rate: 1.689E-04 | global batch size: 256 | lm loss: 2.309259E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.083 | TFLOPs: 20.57 | +31: iteration 11130/ 39672 | consumed samples: 2849280 | consumed tokens: 5835325440 | elapsed time per iteration (s): 0.75 | learning rate: 1.688E-04 | global batch size: 256 | lm loss: 2.271885E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.026 | TFLOPs: 20.69 | +31: iteration 11140/ 39672 | consumed samples: 2851840 | consumed tokens: 5840568320 | elapsed time per iteration (s): 0.99 | learning rate: 1.688E-04 | global batch size: 256 | lm loss: 2.298375E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 258.257 | TFLOPs: 15.62 | +31: iteration 11150/ 39672 | consumed samples: 2854400 | consumed tokens: 5845811200 | elapsed time per iteration (s): 0.79 | learning rate: 1.687E-04 | global batch size: 256 | lm loss: 2.284179E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.696 | TFLOPs: 19.52 | +31: iteration 11160/ 39672 | consumed samples: 2856960 | consumed tokens: 5851054080 | elapsed time per iteration (s): 0.74 | learning rate: 1.687E-04 | global batch size: 256 | lm loss: 2.303500E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.941 | TFLOPs: 20.93 | +31: iteration 11170/ 39672 | consumed samples: 2859520 | consumed tokens: 5856296960 | elapsed time per iteration (s): 0.79 | learning rate: 1.686E-04 | global batch size: 256 | lm loss: 2.291044E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.204 | TFLOPs: 19.49 | +31: iteration 11180/ 39672 | consumed samples: 2862080 | consumed tokens: 5861539840 | elapsed time per iteration (s): 0.78 | learning rate: 1.685E-04 | global batch size: 256 | lm loss: 2.296083E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.420 | TFLOPs: 19.87 | +31: iteration 11190/ 39672 | consumed samples: 2864640 | consumed tokens: 5866782720 | elapsed time per iteration (s): 0.76 | learning rate: 1.685E-04 | global batch size: 256 | lm loss: 2.245219E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.029 | TFLOPs: 20.45 | +31: iteration 11200/ 39672 | consumed samples: 2867200 | consumed tokens: 5872025600 | elapsed time per iteration (s): 0.74 | learning rate: 1.684E-04 | global batch size: 256 | lm loss: 2.333753E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.303 | TFLOPs: 20.95 | +31: iteration 11210/ 39672 | consumed samples: 2869760 | consumed tokens: 5877268480 | elapsed time per iteration (s): 0.77 | learning rate: 1.684E-04 | global batch size: 256 | lm loss: 2.296601E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.437 | TFLOPs: 20.05 | +31: iteration 11220/ 39672 | consumed samples: 2872320 | consumed tokens: 5882511360 | elapsed time per iteration (s): 0.78 | learning rate: 1.683E-04 | global batch size: 256 | lm loss: 2.320201E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.122 | TFLOPs: 19.85 | +31: iteration 11230/ 39672 | consumed samples: 2874880 | consumed tokens: 5887754240 | elapsed time per iteration (s): 0.84 | learning rate: 1.683E-04 | global batch size: 256 | lm loss: 2.303719E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.997 | TFLOPs: 18.45 | +31: iteration 11240/ 39672 | consumed samples: 2877440 | consumed tokens: 5892997120 | elapsed time per iteration (s): 0.80 | learning rate: 1.682E-04 | global batch size: 256 | lm loss: 2.311337E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.935 | TFLOPs: 19.29 | +31: iteration 11250/ 39672 | consumed samples: 2880000 | consumed tokens: 5898240000 | elapsed time per iteration (s): 0.80 | learning rate: 1.682E-04 | global batch size: 256 | lm loss: 2.302653E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.536 | TFLOPs: 19.39 | +31: iteration 11260/ 39672 | consumed samples: 2882560 | consumed tokens: 5903482880 | elapsed time per iteration (s): 0.74 | learning rate: 1.681E-04 | global batch size: 256 | lm loss: 2.288787E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.727 | TFLOPs: 20.92 | +31: iteration 11270/ 39672 | consumed samples: 2885120 | consumed tokens: 5908725760 | elapsed time per iteration (s): 0.74 | learning rate: 1.681E-04 | global batch size: 256 | lm loss: 2.292162E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.199 | TFLOPs: 20.94 | +31: iteration 11280/ 39672 | consumed samples: 2887680 | consumed tokens: 5913968640 | elapsed time per iteration (s): 0.80 | learning rate: 1.680E-04 | global batch size: 256 | lm loss: 2.324603E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.107 | TFLOPs: 19.37 | +31: iteration 11290/ 39672 | consumed samples: 2890240 | consumed tokens: 5919211520 | elapsed time per iteration (s): 0.75 | learning rate: 1.679E-04 | global batch size: 256 | lm loss: 2.283961E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.178 | TFLOPs: 20.58 | +31: iteration 11300/ 39672 | consumed samples: 2892800 | consumed tokens: 5924454400 | elapsed time per iteration (s): 0.72 | learning rate: 1.679E-04 | global batch size: 256 | lm loss: 2.272132E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.368 | TFLOPs: 21.62 | +31: iteration 11310/ 39672 | consumed samples: 2895360 | consumed tokens: 5929697280 | elapsed time per iteration (s): 0.76 | learning rate: 1.678E-04 | global batch size: 256 | lm loss: 2.283117E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.700 | TFLOPs: 20.43 | +31: iteration 11320/ 39672 | consumed samples: 2897920 | consumed tokens: 5934940160 | elapsed time per iteration (s): 0.72 | learning rate: 1.678E-04 | global batch size: 256 | lm loss: 2.276707E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.188 | TFLOPs: 21.37 | +31: iteration 11330/ 39672 | consumed samples: 2900480 | consumed tokens: 5940183040 | elapsed time per iteration (s): 0.81 | learning rate: 1.677E-04 | global batch size: 256 | lm loss: 2.275360E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.452 | TFLOPs: 19.02 | +31: iteration 11340/ 39672 | consumed samples: 2903040 | consumed tokens: 5945425920 | elapsed time per iteration (s): 0.73 | learning rate: 1.677E-04 | global batch size: 256 | lm loss: 2.295044E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.332 | TFLOPs: 21.25 | +31: iteration 11350/ 39672 | consumed samples: 2905600 | consumed tokens: 5950668800 | elapsed time per iteration (s): 0.76 | learning rate: 1.676E-04 | global batch size: 256 | lm loss: 2.300520E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.697 | TFLOPs: 20.37 | +31: iteration 11360/ 39672 | consumed samples: 2908160 | consumed tokens: 5955911680 | elapsed time per iteration (s): 0.73 | learning rate: 1.676E-04 | global batch size: 256 | lm loss: 2.310568E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.043 | TFLOPs: 21.24 | +31: iteration 11370/ 39672 | consumed samples: 2910720 | consumed tokens: 5961154560 | elapsed time per iteration (s): 0.82 | learning rate: 1.675E-04 | global batch size: 256 | lm loss: 2.292364E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.254 | TFLOPs: 18.95 | +31: iteration 11380/ 39672 | consumed samples: 2913280 | consumed tokens: 5966397440 | elapsed time per iteration (s): 0.83 | learning rate: 1.674E-04 | global batch size: 256 | lm loss: 2.286809E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.984 | TFLOPs: 18.75 | +31: iteration 11390/ 39672 | consumed samples: 2915840 | consumed tokens: 5971640320 | elapsed time per iteration (s): 0.78 | learning rate: 1.674E-04 | global batch size: 256 | lm loss: 2.280583E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.565 | TFLOPs: 19.76 | +31: iteration 11400/ 39672 | consumed samples: 2918400 | consumed tokens: 5976883200 | elapsed time per iteration (s): 0.77 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 2.316776E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.453 | TFLOPs: 20.11 | +31: iteration 11410/ 39672 | consumed samples: 2920960 | consumed tokens: 5982126080 | elapsed time per iteration (s): 0.76 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 2.260978E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.183 | TFLOPs: 20.46 | +31: iteration 11420/ 39672 | consumed samples: 2923520 | consumed tokens: 5987368960 | elapsed time per iteration (s): 0.76 | learning rate: 1.672E-04 | global batch size: 256 | lm loss: 2.259030E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.321 | TFLOPs: 20.47 | +31: iteration 11430/ 39672 | consumed samples: 2926080 | consumed tokens: 5992611840 | elapsed time per iteration (s): 0.72 | learning rate: 1.672E-04 | global batch size: 256 | lm loss: 2.278545E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.773 | TFLOPs: 21.52 | +31: iteration 11440/ 39672 | consumed samples: 2928640 | consumed tokens: 5997854720 | elapsed time per iteration (s): 0.75 | learning rate: 1.671E-04 | global batch size: 256 | lm loss: 2.307412E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.566 | TFLOPs: 20.78 | +31: iteration 11450/ 39672 | consumed samples: 2931200 | consumed tokens: 6003097600 | elapsed time per iteration (s): 0.81 | learning rate: 1.671E-04 | global batch size: 256 | lm loss: 2.268447E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.716 | TFLOPs: 19.10 | +31: iteration 11460/ 39672 | consumed samples: 2933760 | consumed tokens: 6008340480 | elapsed time per iteration (s): 0.75 | learning rate: 1.670E-04 | global batch size: 256 | lm loss: 2.284175E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.689 | TFLOPs: 20.73 | +31: iteration 11470/ 39672 | consumed samples: 2936320 | consumed tokens: 6013583360 | elapsed time per iteration (s): 0.78 | learning rate: 1.669E-04 | global batch size: 256 | lm loss: 2.301361E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.459 | TFLOPs: 19.87 | +31: iteration 11480/ 39672 | consumed samples: 2938880 | consumed tokens: 6018826240 | elapsed time per iteration (s): 0.73 | learning rate: 1.669E-04 | global batch size: 256 | lm loss: 2.310955E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.479 | TFLOPs: 21.14 | +31: iteration 11490/ 39672 | consumed samples: 2941440 | consumed tokens: 6024069120 | elapsed time per iteration (s): 0.80 | learning rate: 1.668E-04 | global batch size: 256 | lm loss: 2.294462E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.692 | TFLOPs: 19.40 | +31: iteration 11500/ 39672 | consumed samples: 2944000 | consumed tokens: 6029312000 | elapsed time per iteration (s): 0.74 | learning rate: 1.668E-04 | global batch size: 256 | lm loss: 2.309530E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.078 | TFLOPs: 20.88 | +31: iteration 11510/ 39672 | consumed samples: 2946560 | consumed tokens: 6034554880 | elapsed time per iteration (s): 0.75 | learning rate: 1.667E-04 | global batch size: 256 | lm loss: 2.308665E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.581 | TFLOPs: 20.66 | +31: iteration 11520/ 39672 | consumed samples: 2949120 | consumed tokens: 6039797760 | elapsed time per iteration (s): 0.80 | learning rate: 1.667E-04 | global batch size: 256 | lm loss: 2.286589E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.110 | TFLOPs: 19.24 | +31: iteration 11530/ 39672 | consumed samples: 2951680 | consumed tokens: 6045040640 | elapsed time per iteration (s): 0.80 | learning rate: 1.666E-04 | global batch size: 256 | lm loss: 2.258554E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.194 | TFLOPs: 19.25 | +31: iteration 11540/ 39672 | consumed samples: 2954240 | consumed tokens: 6050283520 | elapsed time per iteration (s): 0.78 | learning rate: 1.666E-04 | global batch size: 256 | lm loss: 2.303556E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.353 | TFLOPs: 19.80 | +31: iteration 11550/ 39672 | consumed samples: 2956800 | consumed tokens: 6055526400 | elapsed time per iteration (s): 0.76 | learning rate: 1.665E-04 | global batch size: 256 | lm loss: 2.298053E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.368 | TFLOPs: 20.41 | +31: iteration 11560/ 39672 | consumed samples: 2959360 | consumed tokens: 6060769280 | elapsed time per iteration (s): 0.77 | learning rate: 1.664E-04 | global batch size: 256 | lm loss: 2.298940E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.733 | TFLOPs: 20.19 | +31: iteration 11570/ 39672 | consumed samples: 2961920 | consumed tokens: 6066012160 | elapsed time per iteration (s): 0.76 | learning rate: 1.664E-04 | global batch size: 256 | lm loss: 2.280028E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.681 | TFLOPs: 20.49 | +31: iteration 11580/ 39672 | consumed samples: 2964480 | consumed tokens: 6071255040 | elapsed time per iteration (s): 0.76 | learning rate: 1.663E-04 | global batch size: 256 | lm loss: 2.260137E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.106 | TFLOPs: 20.33 | +31: iteration 11590/ 39672 | consumed samples: 2967040 | consumed tokens: 6076497920 | elapsed time per iteration (s): 0.72 | learning rate: 1.663E-04 | global batch size: 256 | lm loss: 2.294003E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.319 | TFLOPs: 21.44 | +31: iteration 11600/ 39672 | consumed samples: 2969600 | consumed tokens: 6081740800 | elapsed time per iteration (s): 0.76 | learning rate: 1.662E-04 | global batch size: 256 | lm loss: 2.294603E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.759 | TFLOPs: 20.43 | +31: iteration 11610/ 39672 | consumed samples: 2972160 | consumed tokens: 6086983680 | elapsed time per iteration (s): 0.71 | learning rate: 1.662E-04 | global batch size: 256 | lm loss: 2.292512E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 362.299 | TFLOPs: 21.92 | +31: iteration 11620/ 39672 | consumed samples: 2974720 | consumed tokens: 6092226560 | elapsed time per iteration (s): 0.73 | learning rate: 1.661E-04 | global batch size: 256 | lm loss: 2.322600E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.854 | TFLOPs: 21.29 | +31: iteration 11630/ 39672 | consumed samples: 2977280 | consumed tokens: 6097469440 | elapsed time per iteration (s): 0.76 | learning rate: 1.660E-04 | global batch size: 256 | lm loss: 2.275190E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.836 | TFLOPs: 20.50 | +31: iteration 11640/ 39672 | consumed samples: 2979840 | consumed tokens: 6102712320 | elapsed time per iteration (s): 0.75 | learning rate: 1.660E-04 | global batch size: 256 | lm loss: 2.305671E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.623 | TFLOPs: 20.61 | +31: iteration 11650/ 39672 | consumed samples: 2982400 | consumed tokens: 6107955200 | elapsed time per iteration (s): 0.75 | learning rate: 1.659E-04 | global batch size: 256 | lm loss: 2.259797E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.782 | TFLOPs: 20.62 | +31: iteration 11660/ 39672 | consumed samples: 2984960 | consumed tokens: 6113198080 | elapsed time per iteration (s): 0.75 | learning rate: 1.659E-04 | global batch size: 256 | lm loss: 2.291615E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.334 | TFLOPs: 20.65 | +31: iteration 11670/ 39672 | consumed samples: 2987520 | consumed tokens: 6118440960 | elapsed time per iteration (s): 0.82 | learning rate: 1.658E-04 | global batch size: 256 | lm loss: 2.266568E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.619 | TFLOPs: 18.91 | +31: iteration 11680/ 39672 | consumed samples: 2990080 | consumed tokens: 6123683840 | elapsed time per iteration (s): 0.72 | learning rate: 1.658E-04 | global batch size: 256 | lm loss: 2.306104E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.006 | TFLOPs: 21.42 | +31: iteration 11690/ 39672 | consumed samples: 2992640 | consumed tokens: 6128926720 | elapsed time per iteration (s): 0.83 | learning rate: 1.657E-04 | global batch size: 256 | lm loss: 2.299045E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.141 | TFLOPs: 18.64 | +31: iteration 11700/ 39672 | consumed samples: 2995200 | consumed tokens: 6134169600 | elapsed time per iteration (s): 0.81 | learning rate: 1.657E-04 | global batch size: 256 | lm loss: 2.264966E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.233 | TFLOPs: 19.13 | +31: iteration 11710/ 39672 | consumed samples: 2997760 | consumed tokens: 6139412480 | elapsed time per iteration (s): 0.78 | learning rate: 1.656E-04 | global batch size: 256 | lm loss: 2.288025E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.753 | TFLOPs: 19.77 | +31: iteration 11720/ 39672 | consumed samples: 3000320 | consumed tokens: 6144655360 | elapsed time per iteration (s): 0.78 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 2.274905E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.883 | TFLOPs: 19.90 | +31: iteration 11730/ 39672 | consumed samples: 3002880 | consumed tokens: 6149898240 | elapsed time per iteration (s): 0.75 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 2.278913E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.057 | TFLOPs: 20.63 | +31: iteration 11740/ 39672 | consumed samples: 3005440 | consumed tokens: 6155141120 | elapsed time per iteration (s): 0.73 | learning rate: 1.654E-04 | global batch size: 256 | lm loss: 2.283499E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.809 | TFLOPs: 21.16 | +31: iteration 11750/ 39672 | consumed samples: 3008000 | consumed tokens: 6160384000 | elapsed time per iteration (s): 0.72 | learning rate: 1.654E-04 | global batch size: 256 | lm loss: 2.258965E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.843 | TFLOPs: 21.47 | +31: iteration 11760/ 39672 | consumed samples: 3010560 | consumed tokens: 6165626880 | elapsed time per iteration (s): 0.76 | learning rate: 1.653E-04 | global batch size: 256 | lm loss: 2.292437E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.158 | TFLOPs: 20.46 | +31: iteration 11770/ 39672 | consumed samples: 3013120 | consumed tokens: 6170869760 | elapsed time per iteration (s): 0.77 | learning rate: 1.653E-04 | global batch size: 256 | lm loss: 2.300494E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.125 | TFLOPs: 20.21 | +31: iteration 11780/ 39672 | consumed samples: 3015680 | consumed tokens: 6176112640 | elapsed time per iteration (s): 0.71 | learning rate: 1.652E-04 | global batch size: 256 | lm loss: 2.265600E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 358.113 | TFLOPs: 21.66 | +31: iteration 11790/ 39672 | consumed samples: 3018240 | consumed tokens: 6181355520 | elapsed time per iteration (s): 0.74 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 2.279613E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.498 | TFLOPs: 20.84 | +31: iteration 11800/ 39672 | consumed samples: 3020800 | consumed tokens: 6186598400 | elapsed time per iteration (s): 0.77 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 2.279156E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.020 | TFLOPs: 20.21 | +31: iteration 11810/ 39672 | consumed samples: 3023360 | consumed tokens: 6191841280 | elapsed time per iteration (s): 0.78 | learning rate: 1.650E-04 | global batch size: 256 | lm loss: 2.268362E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.476 | TFLOPs: 19.75 | +31: iteration 11820/ 39672 | consumed samples: 3025920 | consumed tokens: 6197084160 | elapsed time per iteration (s): 0.76 | learning rate: 1.650E-04 | global batch size: 256 | lm loss: 2.282907E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.084 | TFLOPs: 20.27 | +31: iteration 11830/ 39672 | consumed samples: 3028480 | consumed tokens: 6202327040 | elapsed time per iteration (s): 0.79 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 2.235616E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.560 | TFLOPs: 19.70 | +31: iteration 11840/ 39672 | consumed samples: 3031040 | consumed tokens: 6207569920 | elapsed time per iteration (s): 0.77 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 2.278008E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.038 | TFLOPs: 20.21 | +31: iteration 11850/ 39672 | consumed samples: 3033600 | consumed tokens: 6212812800 | elapsed time per iteration (s): 0.83 | learning rate: 1.648E-04 | global batch size: 256 | lm loss: 2.306710E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.533 | TFLOPs: 18.67 | +31: iteration 11860/ 39672 | consumed samples: 3036160 | consumed tokens: 6218055680 | elapsed time per iteration (s): 0.78 | learning rate: 1.647E-04 | global batch size: 256 | lm loss: 2.236693E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.186 | TFLOPs: 19.91 | +31: iteration 11870/ 39672 | consumed samples: 3038720 | consumed tokens: 6223298560 | elapsed time per iteration (s): 0.74 | learning rate: 1.647E-04 | global batch size: 256 | lm loss: 2.283262E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.022 | TFLOPs: 20.87 | +31: iteration 11880/ 39672 | consumed samples: 3041280 | consumed tokens: 6228541440 | elapsed time per iteration (s): 0.74 | learning rate: 1.646E-04 | global batch size: 256 | lm loss: 2.279501E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.765 | TFLOPs: 20.98 | +31: iteration 11890/ 39672 | consumed samples: 3043840 | consumed tokens: 6233784320 | elapsed time per iteration (s): 0.75 | learning rate: 1.646E-04 | global batch size: 256 | lm loss: 2.291530E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.884 | TFLOPs: 20.74 | +31: iteration 11900/ 39672 | consumed samples: 3046400 | consumed tokens: 6239027200 | elapsed time per iteration (s): 0.77 | learning rate: 1.645E-04 | global batch size: 256 | lm loss: 2.253763E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.427 | TFLOPs: 20.23 | +31: iteration 11910/ 39672 | consumed samples: 3048960 | consumed tokens: 6244270080 | elapsed time per iteration (s): 0.76 | learning rate: 1.645E-04 | global batch size: 256 | lm loss: 2.307403E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.328 | TFLOPs: 20.29 | +31: iteration 11920/ 39672 | consumed samples: 3051520 | consumed tokens: 6249512960 | elapsed time per iteration (s): 0.79 | learning rate: 1.644E-04 | global batch size: 256 | lm loss: 2.304220E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.945 | TFLOPs: 19.54 | +31: iteration 11930/ 39672 | consumed samples: 3054080 | consumed tokens: 6254755840 | elapsed time per iteration (s): 0.71 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 2.302189E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.411 | TFLOPs: 21.74 | +31: iteration 11940/ 39672 | consumed samples: 3056640 | consumed tokens: 6259998720 | elapsed time per iteration (s): 0.73 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 2.298309E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.621 | TFLOPs: 21.33 | +31: iteration 11950/ 39672 | consumed samples: 3059200 | consumed tokens: 6265241600 | elapsed time per iteration (s): 0.73 | learning rate: 1.642E-04 | global batch size: 256 | lm loss: 2.241165E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.328 | TFLOPs: 21.07 | +31: iteration 11960/ 39672 | consumed samples: 3061760 | consumed tokens: 6270484480 | elapsed time per iteration (s): 0.78 | learning rate: 1.642E-04 | global batch size: 256 | lm loss: 2.280420E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.247 | TFLOPs: 19.74 | +31: iteration 11970/ 39672 | consumed samples: 3064320 | consumed tokens: 6275727360 | elapsed time per iteration (s): 0.80 | learning rate: 1.641E-04 | global batch size: 256 | lm loss: 2.279068E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.483 | TFLOPs: 19.45 | +31: iteration 11980/ 39672 | consumed samples: 3066880 | consumed tokens: 6280970240 | elapsed time per iteration (s): 0.77 | learning rate: 1.641E-04 | global batch size: 256 | lm loss: 2.307790E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.256 | TFLOPs: 20.22 | +31: iteration 11990/ 39672 | consumed samples: 3069440 | consumed tokens: 6286213120 | elapsed time per iteration (s): 0.75 | learning rate: 1.640E-04 | global batch size: 256 | lm loss: 2.280594E+00 | grad norm: 1.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.099 | TFLOPs: 20.51 | + 0: [2022-11-30 11:52:50,485] [INFO] [logging.py:68:log_dist] [Rank 0] step=12000, skipped=0, lr=[0.00016394097738991364, 0.00016394097738991364, 0.00016394097738991364], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 12000/ 39672 | consumed samples: 3072000 | consumed tokens: 6291456000 | elapsed time per iteration (s): 0.77 | learning rate: 1.639E-04 | global batch size: 256 | lm loss: 2.827100E+00 | grad norm: 30.011 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.781 | TFLOPs: 20.01 | + 0: steps: 12000 loss: 3.8527 iter time (s): 0.776 samples/sec: 330.046 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 12000 | lm loss value: 5.837679E+00 | lm loss PPL: 3.429825E+02 | +31: ------------------------------------------------------------------------------------------- +31: iteration 12010/ 39672 | consumed samples: 3074560 | consumed tokens: 6296698880 | elapsed time per iteration (s): 0.89 | learning rate: 1.639E-04 | global batch size: 256 | lm loss: 3.636695E+00 | grad norm: 2.619 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 288.714 | TFLOPs: 17.47 | +31: iteration 12020/ 39672 | consumed samples: 3077120 | consumed tokens: 6301941760 | elapsed time per iteration (s): 0.82 | learning rate: 1.638E-04 | global batch size: 256 | lm loss: 2.476381E+00 | grad norm: 0.708 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.928 | TFLOPs: 18.87 | +31: iteration 12030/ 39672 | consumed samples: 3079680 | consumed tokens: 6307184640 | elapsed time per iteration (s): 0.87 | learning rate: 1.638E-04 | global batch size: 256 | lm loss: 2.344548E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 294.848 | TFLOPs: 17.84 | +31: iteration 12040/ 39672 | consumed samples: 3082240 | consumed tokens: 6312427520 | elapsed time per iteration (s): 0.84 | learning rate: 1.637E-04 | global batch size: 256 | lm loss: 2.319222E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.555 | TFLOPs: 18.49 | +31: iteration 12050/ 39672 | consumed samples: 3084800 | consumed tokens: 6317670400 | elapsed time per iteration (s): 0.82 | learning rate: 1.637E-04 | global batch size: 256 | lm loss: 2.285186E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.011 | TFLOPs: 18.94 | +31: iteration 12060/ 39672 | consumed samples: 3087360 | consumed tokens: 6322913280 | elapsed time per iteration (s): 0.77 | learning rate: 1.636E-04 | global batch size: 256 | lm loss: 2.283613E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.150 | TFLOPs: 20.09 | +31: iteration 12070/ 39672 | consumed samples: 3089920 | consumed tokens: 6328156160 | elapsed time per iteration (s): 0.84 | learning rate: 1.635E-04 | global batch size: 256 | lm loss: 2.303279E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.755 | TFLOPs: 18.50 | +31: iteration 12080/ 39672 | consumed samples: 3092480 | consumed tokens: 6333399040 | elapsed time per iteration (s): 0.83 | learning rate: 1.635E-04 | global batch size: 256 | lm loss: 2.282661E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.369 | TFLOPs: 18.60 | +31: iteration 12090/ 39672 | consumed samples: 3095040 | consumed tokens: 6338641920 | elapsed time per iteration (s): 0.81 | learning rate: 1.634E-04 | global batch size: 256 | lm loss: 2.275186E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.455 | TFLOPs: 19.08 | +31: iteration 12100/ 39672 | consumed samples: 3097600 | consumed tokens: 6343884800 | elapsed time per iteration (s): 0.83 | learning rate: 1.634E-04 | global batch size: 256 | lm loss: 2.271206E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.545 | TFLOPs: 18.61 | +31: iteration 12110/ 39672 | consumed samples: 3100160 | consumed tokens: 6349127680 | elapsed time per iteration (s): 0.81 | learning rate: 1.633E-04 | global batch size: 256 | lm loss: 2.245292E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.973 | TFLOPs: 19.18 | +31: iteration 12120/ 39672 | consumed samples: 3102720 | consumed tokens: 6354370560 | elapsed time per iteration (s): 0.80 | learning rate: 1.632E-04 | global batch size: 256 | lm loss: 2.298226E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.314 | TFLOPs: 19.38 | +31: iteration 12130/ 39672 | consumed samples: 3105280 | consumed tokens: 6359613440 | elapsed time per iteration (s): 0.80 | learning rate: 1.632E-04 | global batch size: 256 | lm loss: 2.301512E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.373 | TFLOPs: 19.26 | +31: iteration 12140/ 39672 | consumed samples: 3107840 | consumed tokens: 6364856320 | elapsed time per iteration (s): 0.83 | learning rate: 1.631E-04 | global batch size: 256 | lm loss: 2.295897E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.084 | TFLOPs: 18.76 | +31: iteration 12150/ 39672 | consumed samples: 3110400 | consumed tokens: 6370099200 | elapsed time per iteration (s): 0.80 | learning rate: 1.631E-04 | global batch size: 256 | lm loss: 2.305568E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.740 | TFLOPs: 19.28 | +31: iteration 12160/ 39672 | consumed samples: 3112960 | consumed tokens: 6375342080 | elapsed time per iteration (s): 0.80 | learning rate: 1.630E-04 | global batch size: 256 | lm loss: 2.265123E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.866 | TFLOPs: 19.41 | +31: iteration 12170/ 39672 | consumed samples: 3115520 | consumed tokens: 6380584960 | elapsed time per iteration (s): 0.81 | learning rate: 1.630E-04 | global batch size: 256 | lm loss: 2.227453E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.638 | TFLOPs: 19.16 | +31: iteration 12180/ 39672 | consumed samples: 3118080 | consumed tokens: 6385827840 | elapsed time per iteration (s): 0.84 | learning rate: 1.629E-04 | global batch size: 256 | lm loss: 2.266424E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.248 | TFLOPs: 18.53 | +31: iteration 12190/ 39672 | consumed samples: 3120640 | consumed tokens: 6391070720 | elapsed time per iteration (s): 0.80 | learning rate: 1.628E-04 | global batch size: 256 | lm loss: 2.263537E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.540 | TFLOPs: 19.27 | +31: iteration 12200/ 39672 | consumed samples: 3123200 | consumed tokens: 6396313600 | elapsed time per iteration (s): 0.83 | learning rate: 1.628E-04 | global batch size: 256 | lm loss: 2.294328E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.592 | TFLOPs: 18.73 | +31: iteration 12210/ 39672 | consumed samples: 3125760 | consumed tokens: 6401556480 | elapsed time per iteration (s): 0.83 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 2.292188E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.118 | TFLOPs: 18.76 | +31: iteration 12220/ 39672 | consumed samples: 3128320 | consumed tokens: 6406799360 | elapsed time per iteration (s): 0.81 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 2.280226E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.439 | TFLOPs: 19.20 | +31: iteration 12230/ 39672 | consumed samples: 3130880 | consumed tokens: 6412042240 | elapsed time per iteration (s): 0.81 | learning rate: 1.626E-04 | global batch size: 256 | lm loss: 2.282450E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.297 | TFLOPs: 19.20 | +31: iteration 12240/ 39672 | consumed samples: 3133440 | consumed tokens: 6417285120 | elapsed time per iteration (s): 0.81 | learning rate: 1.625E-04 | global batch size: 256 | lm loss: 2.249059E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.226 | TFLOPs: 19.07 | +31: iteration 12250/ 39672 | consumed samples: 3136000 | consumed tokens: 6422528000 | elapsed time per iteration (s): 0.82 | learning rate: 1.625E-04 | global batch size: 256 | lm loss: 2.278362E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.501 | TFLOPs: 18.85 | +31: iteration 12260/ 39672 | consumed samples: 3138560 | consumed tokens: 6427770880 | elapsed time per iteration (s): 0.81 | learning rate: 1.624E-04 | global batch size: 256 | lm loss: 2.279954E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.390 | TFLOPs: 19.20 | +31: iteration 12270/ 39672 | consumed samples: 3141120 | consumed tokens: 6433013760 | elapsed time per iteration (s): 0.86 | learning rate: 1.624E-04 | global batch size: 256 | lm loss: 2.281438E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.335 | TFLOPs: 18.05 | +31: iteration 12280/ 39672 | consumed samples: 3143680 | consumed tokens: 6438256640 | elapsed time per iteration (s): 0.80 | learning rate: 1.623E-04 | global batch size: 256 | lm loss: 2.275925E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.881 | TFLOPs: 19.41 | +31: iteration 12290/ 39672 | consumed samples: 3146240 | consumed tokens: 6443499520 | elapsed time per iteration (s): 0.80 | learning rate: 1.623E-04 | global batch size: 256 | lm loss: 2.285188E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.074 | TFLOPs: 19.24 | +31: iteration 12300/ 39672 | consumed samples: 3148800 | consumed tokens: 6448742400 | elapsed time per iteration (s): 0.77 | learning rate: 1.622E-04 | global batch size: 256 | lm loss: 2.273882E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.597 | TFLOPs: 20.24 | +31: iteration 12310/ 39672 | consumed samples: 3151360 | consumed tokens: 6453985280 | elapsed time per iteration (s): 0.73 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 2.295117E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.773 | TFLOPs: 21.28 | +31: iteration 12320/ 39672 | consumed samples: 3153920 | consumed tokens: 6459228160 | elapsed time per iteration (s): 0.79 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 2.259466E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.090 | TFLOPs: 19.61 | +31: iteration 12330/ 39672 | consumed samples: 3156480 | consumed tokens: 6464471040 | elapsed time per iteration (s): 0.83 | learning rate: 1.620E-04 | global batch size: 256 | lm loss: 2.297521E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.273 | TFLOPs: 18.77 | +31: iteration 12340/ 39672 | consumed samples: 3159040 | consumed tokens: 6469713920 | elapsed time per iteration (s): 0.75 | learning rate: 1.620E-04 | global batch size: 256 | lm loss: 2.283414E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.851 | TFLOPs: 20.74 | +31: iteration 12350/ 39672 | consumed samples: 3161600 | consumed tokens: 6474956800 | elapsed time per iteration (s): 0.76 | learning rate: 1.619E-04 | global batch size: 256 | lm loss: 2.278429E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.790 | TFLOPs: 20.50 | +31: iteration 12360/ 39672 | consumed samples: 3164160 | consumed tokens: 6480199680 | elapsed time per iteration (s): 0.79 | learning rate: 1.618E-04 | global batch size: 256 | lm loss: 2.278363E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.177 | TFLOPs: 19.49 | +31: iteration 12370/ 39672 | consumed samples: 3166720 | consumed tokens: 6485442560 | elapsed time per iteration (s): 0.82 | learning rate: 1.618E-04 | global batch size: 256 | lm loss: 2.267802E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.875 | TFLOPs: 18.87 | +31: iteration 12380/ 39672 | consumed samples: 3169280 | consumed tokens: 6490685440 | elapsed time per iteration (s): 0.84 | learning rate: 1.617E-04 | global batch size: 256 | lm loss: 2.280275E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.640 | TFLOPs: 18.37 | +31: iteration 12390/ 39672 | consumed samples: 3171840 | consumed tokens: 6495928320 | elapsed time per iteration (s): 0.80 | learning rate: 1.617E-04 | global batch size: 256 | lm loss: 2.246846E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.086 | TFLOPs: 19.36 | +31: iteration 12400/ 39672 | consumed samples: 3174400 | consumed tokens: 6501171200 | elapsed time per iteration (s): 0.73 | learning rate: 1.616E-04 | global batch size: 256 | lm loss: 2.297200E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.204 | TFLOPs: 21.31 | +31: iteration 12410/ 39672 | consumed samples: 3176960 | consumed tokens: 6506414080 | elapsed time per iteration (s): 0.85 | learning rate: 1.615E-04 | global batch size: 256 | lm loss: 2.300700E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.531 | TFLOPs: 18.12 | +31: iteration 12420/ 39672 | consumed samples: 3179520 | consumed tokens: 6511656960 | elapsed time per iteration (s): 0.81 | learning rate: 1.615E-04 | global batch size: 256 | lm loss: 2.270405E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.994 | TFLOPs: 19.24 | +31: iteration 12430/ 39672 | consumed samples: 3182080 | consumed tokens: 6516899840 | elapsed time per iteration (s): 0.75 | learning rate: 1.614E-04 | global batch size: 256 | lm loss: 2.279823E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.498 | TFLOPs: 20.78 | +31: iteration 12440/ 39672 | consumed samples: 3184640 | consumed tokens: 6522142720 | elapsed time per iteration (s): 0.78 | learning rate: 1.614E-04 | global batch size: 256 | lm loss: 2.252974E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.267 | TFLOPs: 19.98 | +31: iteration 12450/ 39672 | consumed samples: 3187200 | consumed tokens: 6527385600 | elapsed time per iteration (s): 0.78 | learning rate: 1.613E-04 | global batch size: 256 | lm loss: 2.272269E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.373 | TFLOPs: 19.93 | +31: iteration 12460/ 39672 | consumed samples: 3189760 | consumed tokens: 6532628480 | elapsed time per iteration (s): 0.82 | learning rate: 1.613E-04 | global batch size: 256 | lm loss: 2.300866E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.820 | TFLOPs: 18.92 | +31: iteration 12470/ 39672 | consumed samples: 3192320 | consumed tokens: 6537871360 | elapsed time per iteration (s): 0.87 | learning rate: 1.612E-04 | global batch size: 256 | lm loss: 2.271588E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 293.523 | TFLOPs: 17.76 | +31: iteration 12480/ 39672 | consumed samples: 3194880 | consumed tokens: 6543114240 | elapsed time per iteration (s): 0.83 | learning rate: 1.611E-04 | global batch size: 256 | lm loss: 2.248735E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.143 | TFLOPs: 18.76 | +31: iteration 12490/ 39672 | consumed samples: 3197440 | consumed tokens: 6548357120 | elapsed time per iteration (s): 0.81 | learning rate: 1.611E-04 | global batch size: 256 | lm loss: 2.246633E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.668 | TFLOPs: 19.10 | +31: iteration 12500/ 39672 | consumed samples: 3200000 | consumed tokens: 6553600000 | elapsed time per iteration (s): 0.81 | learning rate: 1.610E-04 | global batch size: 256 | lm loss: 2.249248E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.674 | TFLOPs: 19.10 | +31: iteration 12510/ 39672 | consumed samples: 3202560 | consumed tokens: 6558842880 | elapsed time per iteration (s): 0.78 | learning rate: 1.610E-04 | global batch size: 256 | lm loss: 2.253412E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.875 | TFLOPs: 19.84 | +31: iteration 12520/ 39672 | consumed samples: 3205120 | consumed tokens: 6564085760 | elapsed time per iteration (s): 0.76 | learning rate: 1.609E-04 | global batch size: 256 | lm loss: 2.278549E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.309 | TFLOPs: 20.29 | +31: iteration 12530/ 39672 | consumed samples: 3207680 | consumed tokens: 6569328640 | elapsed time per iteration (s): 0.73 | learning rate: 1.608E-04 | global batch size: 256 | lm loss: 2.256747E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.511 | TFLOPs: 21.21 | +31: iteration 12540/ 39672 | consumed samples: 3210240 | consumed tokens: 6574571520 | elapsed time per iteration (s): 0.74 | learning rate: 1.608E-04 | global batch size: 256 | lm loss: 2.240099E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.299 | TFLOPs: 20.83 | +31: iteration 12550/ 39672 | consumed samples: 3212800 | consumed tokens: 6579814400 | elapsed time per iteration (s): 0.82 | learning rate: 1.607E-04 | global batch size: 256 | lm loss: 2.271604E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.635 | TFLOPs: 18.97 | +31: iteration 12560/ 39672 | consumed samples: 3215360 | consumed tokens: 6585057280 | elapsed time per iteration (s): 0.85 | learning rate: 1.607E-04 | global batch size: 256 | lm loss: 2.305829E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.929 | TFLOPs: 18.27 | +31: iteration 12570/ 39672 | consumed samples: 3217920 | consumed tokens: 6590300160 | elapsed time per iteration (s): 0.83 | learning rate: 1.606E-04 | global batch size: 256 | lm loss: 2.268459E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.981 | TFLOPs: 18.69 | +31: iteration 12580/ 39672 | consumed samples: 3220480 | consumed tokens: 6595543040 | elapsed time per iteration (s): 0.81 | learning rate: 1.605E-04 | global batch size: 256 | lm loss: 2.271127E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.433 | TFLOPs: 19.20 | +31: iteration 12590/ 39672 | consumed samples: 3223040 | consumed tokens: 6600785920 | elapsed time per iteration (s): 0.81 | learning rate: 1.605E-04 | global batch size: 256 | lm loss: 2.289373E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.862 | TFLOPs: 19.23 | +31: iteration 12600/ 39672 | consumed samples: 3225600 | consumed tokens: 6606028800 | elapsed time per iteration (s): 0.82 | learning rate: 1.604E-04 | global batch size: 256 | lm loss: 2.264917E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.221 | TFLOPs: 18.95 | +31: iteration 12610/ 39672 | consumed samples: 3228160 | consumed tokens: 6611271680 | elapsed time per iteration (s): 0.83 | learning rate: 1.604E-04 | global batch size: 256 | lm loss: 2.259175E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.106 | TFLOPs: 18.76 | +31: iteration 12620/ 39672 | consumed samples: 3230720 | consumed tokens: 6616514560 | elapsed time per iteration (s): 0.82 | learning rate: 1.603E-04 | global batch size: 256 | lm loss: 2.239244E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.010 | TFLOPs: 19.00 | +31: iteration 12630/ 39672 | consumed samples: 3233280 | consumed tokens: 6621757440 | elapsed time per iteration (s): 0.79 | learning rate: 1.602E-04 | global batch size: 256 | lm loss: 2.293677E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.488 | TFLOPs: 19.69 | +31: iteration 12640/ 39672 | consumed samples: 3235840 | consumed tokens: 6627000320 | elapsed time per iteration (s): 0.78 | learning rate: 1.602E-04 | global batch size: 256 | lm loss: 2.271842E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.690 | TFLOPs: 19.88 | +31: iteration 12650/ 39672 | consumed samples: 3238400 | consumed tokens: 6632243200 | elapsed time per iteration (s): 0.88 | learning rate: 1.601E-04 | global batch size: 256 | lm loss: 2.249919E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 291.675 | TFLOPs: 17.65 | +31: iteration 12660/ 39672 | consumed samples: 3240960 | consumed tokens: 6637486080 | elapsed time per iteration (s): 0.82 | learning rate: 1.601E-04 | global batch size: 256 | lm loss: 2.261193E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.640 | TFLOPs: 18.85 | +31: iteration 12670/ 39672 | consumed samples: 3243520 | consumed tokens: 6642728960 | elapsed time per iteration (s): 0.80 | learning rate: 1.600E-04 | global batch size: 256 | lm loss: 2.259756E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.486 | TFLOPs: 19.27 | +31: iteration 12680/ 39672 | consumed samples: 3246080 | consumed tokens: 6647971840 | elapsed time per iteration (s): 0.85 | learning rate: 1.599E-04 | global batch size: 256 | lm loss: 2.290370E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.058 | TFLOPs: 18.21 | +31: iteration 12690/ 39672 | consumed samples: 3248640 | consumed tokens: 6653214720 | elapsed time per iteration (s): 0.84 | learning rate: 1.599E-04 | global batch size: 256 | lm loss: 2.251930E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.259 | TFLOPs: 18.41 | +31: iteration 12700/ 39672 | consumed samples: 3251200 | consumed tokens: 6658457600 | elapsed time per iteration (s): 0.80 | learning rate: 1.598E-04 | global batch size: 256 | lm loss: 2.267049E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.648 | TFLOPs: 19.28 | +31: iteration 12710/ 39672 | consumed samples: 3253760 | consumed tokens: 6663700480 | elapsed time per iteration (s): 0.79 | learning rate: 1.598E-04 | global batch size: 256 | lm loss: 2.253751E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.807 | TFLOPs: 19.53 | +31: iteration 12720/ 39672 | consumed samples: 3256320 | consumed tokens: 6668943360 | elapsed time per iteration (s): 0.86 | learning rate: 1.597E-04 | global batch size: 256 | lm loss: 2.249808E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.567 | TFLOPs: 18.06 | +31: iteration 12730/ 39672 | consumed samples: 3258880 | consumed tokens: 6674186240 | elapsed time per iteration (s): 0.82 | learning rate: 1.596E-04 | global batch size: 256 | lm loss: 2.240942E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.065 | TFLOPs: 18.88 | +31: iteration 12740/ 39672 | consumed samples: 3261440 | consumed tokens: 6679429120 | elapsed time per iteration (s): 0.80 | learning rate: 1.596E-04 | global batch size: 256 | lm loss: 2.252954E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.669 | TFLOPs: 19.40 | +31: iteration 12750/ 39672 | consumed samples: 3264000 | consumed tokens: 6684672000 | elapsed time per iteration (s): 0.79 | learning rate: 1.595E-04 | global batch size: 256 | lm loss: 2.289812E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.209 | TFLOPs: 19.49 | +31: iteration 12760/ 39672 | consumed samples: 3266560 | consumed tokens: 6689914880 | elapsed time per iteration (s): 0.82 | learning rate: 1.595E-04 | global batch size: 256 | lm loss: 2.263172E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.463 | TFLOPs: 18.78 | +31: iteration 12770/ 39672 | consumed samples: 3269120 | consumed tokens: 6695157760 | elapsed time per iteration (s): 0.82 | learning rate: 1.594E-04 | global batch size: 256 | lm loss: 2.251135E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.868 | TFLOPs: 18.87 | +31: iteration 12780/ 39672 | consumed samples: 3271680 | consumed tokens: 6700400640 | elapsed time per iteration (s): 0.85 | learning rate: 1.593E-04 | global batch size: 256 | lm loss: 2.266208E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.303 | TFLOPs: 18.29 | +31: iteration 12790/ 39672 | consumed samples: 3274240 | consumed tokens: 6705643520 | elapsed time per iteration (s): 0.84 | learning rate: 1.593E-04 | global batch size: 256 | lm loss: 2.252337E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.499 | TFLOPs: 18.48 | +31: iteration 12800/ 39672 | consumed samples: 3276800 | consumed tokens: 6710886400 | elapsed time per iteration (s): 0.86 | learning rate: 1.592E-04 | global batch size: 256 | lm loss: 2.277462E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.032 | TFLOPs: 17.91 | +31: iteration 12810/ 39672 | consumed samples: 3279360 | consumed tokens: 6716129280 | elapsed time per iteration (s): 0.84 | learning rate: 1.592E-04 | global batch size: 256 | lm loss: 2.273089E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.799 | TFLOPs: 18.50 | +31: iteration 12820/ 39672 | consumed samples: 3281920 | consumed tokens: 6721372160 | elapsed time per iteration (s): 0.81 | learning rate: 1.591E-04 | global batch size: 256 | lm loss: 2.262054E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.541 | TFLOPs: 19.21 | +31: iteration 12830/ 39672 | consumed samples: 3284480 | consumed tokens: 6726615040 | elapsed time per iteration (s): 0.80 | learning rate: 1.590E-04 | global batch size: 256 | lm loss: 2.264627E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.710 | TFLOPs: 19.46 | +31: iteration 12840/ 39672 | consumed samples: 3287040 | consumed tokens: 6731857920 | elapsed time per iteration (s): 0.83 | learning rate: 1.590E-04 | global batch size: 256 | lm loss: 2.261461E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.787 | TFLOPs: 18.68 | +31: iteration 12850/ 39672 | consumed samples: 3289600 | consumed tokens: 6737100800 | elapsed time per iteration (s): 0.81 | learning rate: 1.589E-04 | global batch size: 256 | lm loss: 2.222521E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.251 | TFLOPs: 19.19 | +31: iteration 12860/ 39672 | consumed samples: 3292160 | consumed tokens: 6742343680 | elapsed time per iteration (s): 0.84 | learning rate: 1.589E-04 | global batch size: 256 | lm loss: 2.253638E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.746 | TFLOPs: 18.50 | +31: iteration 12870/ 39672 | consumed samples: 3294720 | consumed tokens: 6747586560 | elapsed time per iteration (s): 0.80 | learning rate: 1.588E-04 | global batch size: 256 | lm loss: 2.252163E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.295 | TFLOPs: 19.38 | +31: iteration 12880/ 39672 | consumed samples: 3297280 | consumed tokens: 6752829440 | elapsed time per iteration (s): 0.85 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 2.269098E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.335 | TFLOPs: 18.17 | +31: iteration 12890/ 39672 | consumed samples: 3299840 | consumed tokens: 6758072320 | elapsed time per iteration (s): 0.82 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 2.270351E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.512 | TFLOPs: 18.79 | +31: iteration 12900/ 39672 | consumed samples: 3302400 | consumed tokens: 6763315200 | elapsed time per iteration (s): 0.84 | learning rate: 1.586E-04 | global batch size: 256 | lm loss: 2.262558E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.431 | TFLOPs: 18.48 | +31: iteration 12910/ 39672 | consumed samples: 3304960 | consumed tokens: 6768558080 | elapsed time per iteration (s): 0.79 | learning rate: 1.586E-04 | global batch size: 256 | lm loss: 2.262298E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.488 | TFLOPs: 19.63 | +31: iteration 12920/ 39672 | consumed samples: 3307520 | consumed tokens: 6773800960 | elapsed time per iteration (s): 0.89 | learning rate: 1.585E-04 | global batch size: 256 | lm loss: 2.300416E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 289.214 | TFLOPs: 17.50 | +31: iteration 12930/ 39672 | consumed samples: 3310080 | consumed tokens: 6779043840 | elapsed time per iteration (s): 0.84 | learning rate: 1.584E-04 | global batch size: 256 | lm loss: 2.272978E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.934 | TFLOPs: 18.51 | +31: iteration 12940/ 39672 | consumed samples: 3312640 | consumed tokens: 6784286720 | elapsed time per iteration (s): 0.85 | learning rate: 1.584E-04 | global batch size: 256 | lm loss: 2.274148E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.872 | TFLOPs: 18.32 | +31: iteration 12950/ 39672 | consumed samples: 3315200 | consumed tokens: 6789529600 | elapsed time per iteration (s): 0.78 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 2.253865E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.601 | TFLOPs: 19.94 | +31: iteration 12960/ 39672 | consumed samples: 3317760 | consumed tokens: 6794772480 | elapsed time per iteration (s): 0.78 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 2.231849E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.164 | TFLOPs: 19.73 | +31: iteration 12970/ 39672 | consumed samples: 3320320 | consumed tokens: 6800015360 | elapsed time per iteration (s): 0.82 | learning rate: 1.582E-04 | global batch size: 256 | lm loss: 2.243993E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.486 | TFLOPs: 18.90 | +31: iteration 12980/ 39672 | consumed samples: 3322880 | consumed tokens: 6805258240 | elapsed time per iteration (s): 0.80 | learning rate: 1.581E-04 | global batch size: 256 | lm loss: 2.276052E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.516 | TFLOPs: 19.33 | +31: iteration 12990/ 39672 | consumed samples: 3325440 | consumed tokens: 6810501120 | elapsed time per iteration (s): 0.85 | learning rate: 1.581E-04 | global batch size: 256 | lm loss: 2.229281E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.556 | TFLOPs: 18.24 | +31: iteration 13000/ 39672 | consumed samples: 3328000 | consumed tokens: 6815744000 | elapsed time per iteration (s): 0.81 | learning rate: 1.580E-04 | global batch size: 256 | lm loss: 2.268859E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.165 | TFLOPs: 19.19 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 13000 | lm loss value: 2.219772E+00 | lm loss PPL: 9.205228E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 13010/ 39672 | consumed samples: 3330560 | consumed tokens: 6820986880 | elapsed time per iteration (s): 0.84 | learning rate: 1.580E-04 | global batch size: 256 | lm loss: 2.274659E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.053 | TFLOPs: 18.52 | +31: iteration 13020/ 39672 | consumed samples: 3333120 | consumed tokens: 6826229760 | elapsed time per iteration (s): 0.81 | learning rate: 1.579E-04 | global batch size: 256 | lm loss: 2.253966E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.609 | TFLOPs: 19.15 | +31: iteration 13030/ 39672 | consumed samples: 3335680 | consumed tokens: 6831472640 | elapsed time per iteration (s): 0.80 | learning rate: 1.578E-04 | global batch size: 256 | lm loss: 2.240948E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.165 | TFLOPs: 19.37 | +31: iteration 13040/ 39672 | consumed samples: 3338240 | consumed tokens: 6836715520 | elapsed time per iteration (s): 0.74 | learning rate: 1.578E-04 | global batch size: 256 | lm loss: 2.261376E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.994 | TFLOPs: 20.99 | +31: iteration 13050/ 39672 | consumed samples: 3340800 | consumed tokens: 6841958400 | elapsed time per iteration (s): 0.75 | learning rate: 1.577E-04 | global batch size: 256 | lm loss: 2.223921E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.111 | TFLOPs: 20.76 | +31: iteration 13060/ 39672 | consumed samples: 3343360 | consumed tokens: 6847201280 | elapsed time per iteration (s): 0.73 | learning rate: 1.576E-04 | global batch size: 256 | lm loss: 2.249853E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.822 | TFLOPs: 21.34 | +31: iteration 13070/ 39672 | consumed samples: 3345920 | consumed tokens: 6852444160 | elapsed time per iteration (s): 0.76 | learning rate: 1.576E-04 | global batch size: 256 | lm loss: 2.265773E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.936 | TFLOPs: 20.50 | +31: iteration 13080/ 39672 | consumed samples: 3348480 | consumed tokens: 6857687040 | elapsed time per iteration (s): 0.75 | learning rate: 1.575E-04 | global batch size: 256 | lm loss: 2.282546E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.145 | TFLOPs: 20.58 | +31: iteration 13090/ 39672 | consumed samples: 3351040 | consumed tokens: 6862929920 | elapsed time per iteration (s): 0.78 | learning rate: 1.575E-04 | global batch size: 256 | lm loss: 2.250317E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.678 | TFLOPs: 19.94 | +31: iteration 13100/ 39672 | consumed samples: 3353600 | consumed tokens: 6868172800 | elapsed time per iteration (s): 0.74 | learning rate: 1.574E-04 | global batch size: 256 | lm loss: 2.282657E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.722 | TFLOPs: 21.04 | +31: iteration 13110/ 39672 | consumed samples: 3356160 | consumed tokens: 6873415680 | elapsed time per iteration (s): 0.81 | learning rate: 1.573E-04 | global batch size: 256 | lm loss: 2.251556E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.367 | TFLOPs: 19.14 | +31: iteration 13120/ 39672 | consumed samples: 3358720 | consumed tokens: 6878658560 | elapsed time per iteration (s): 0.78 | learning rate: 1.573E-04 | global batch size: 256 | lm loss: 2.259855E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.737 | TFLOPs: 19.89 | +31: iteration 13130/ 39672 | consumed samples: 3361280 | consumed tokens: 6883901440 | elapsed time per iteration (s): 0.80 | learning rate: 1.572E-04 | global batch size: 256 | lm loss: 2.237655E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.097 | TFLOPs: 19.30 | +31: iteration 13140/ 39672 | consumed samples: 3363840 | consumed tokens: 6889144320 | elapsed time per iteration (s): 0.81 | learning rate: 1.572E-04 | global batch size: 256 | lm loss: 2.214569E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.506 | TFLOPs: 19.15 | +31: iteration 13150/ 39672 | consumed samples: 3366400 | consumed tokens: 6894387200 | elapsed time per iteration (s): 0.80 | learning rate: 1.571E-04 | global batch size: 256 | lm loss: 2.262523E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.376 | TFLOPs: 19.38 | +31: iteration 13160/ 39672 | consumed samples: 3368960 | consumed tokens: 6899630080 | elapsed time per iteration (s): 0.79 | learning rate: 1.570E-04 | global batch size: 256 | lm loss: 2.265756E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.664 | TFLOPs: 19.70 | +31: iteration 13170/ 39672 | consumed samples: 3371520 | consumed tokens: 6904872960 | elapsed time per iteration (s): 0.75 | learning rate: 1.570E-04 | global batch size: 256 | lm loss: 2.256405E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.361 | TFLOPs: 20.65 | +31: iteration 13180/ 39672 | consumed samples: 3374080 | consumed tokens: 6910115840 | elapsed time per iteration (s): 0.80 | learning rate: 1.569E-04 | global batch size: 256 | lm loss: 2.225135E+00 | grad norm: 0.625 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.269 | TFLOPs: 19.31 | +31: iteration 13190/ 39672 | consumed samples: 3376640 | consumed tokens: 6915358720 | elapsed time per iteration (s): 0.76 | learning rate: 1.568E-04 | global batch size: 256 | lm loss: 2.404719E+00 | grad norm: 3.048 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.698 | TFLOPs: 20.49 | +31: iteration 13200/ 39672 | consumed samples: 3379200 | consumed tokens: 6920601600 | elapsed time per iteration (s): 0.78 | learning rate: 1.568E-04 | global batch size: 256 | lm loss: 2.646505E+00 | grad norm: 0.498 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.748 | TFLOPs: 19.77 | +31: iteration 13210/ 39672 | consumed samples: 3381760 | consumed tokens: 6925844480 | elapsed time per iteration (s): 0.74 | learning rate: 1.567E-04 | global batch size: 256 | lm loss: 2.305501E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.180 | TFLOPs: 20.94 | +31: iteration 13220/ 39672 | consumed samples: 3384320 | consumed tokens: 6931087360 | elapsed time per iteration (s): 0.73 | learning rate: 1.567E-04 | global batch size: 256 | lm loss: 2.318882E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.079 | TFLOPs: 21.30 | +31: iteration 13230/ 39672 | consumed samples: 3386880 | consumed tokens: 6936330240 | elapsed time per iteration (s): 0.71 | learning rate: 1.566E-04 | global batch size: 256 | lm loss: 2.294243E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.213 | TFLOPs: 21.73 | +31: iteration 13240/ 39672 | consumed samples: 3389440 | consumed tokens: 6941573120 | elapsed time per iteration (s): 0.74 | learning rate: 1.565E-04 | global batch size: 256 | lm loss: 2.279646E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.051 | TFLOPs: 21.00 | +31: iteration 13250/ 39672 | consumed samples: 3392000 | consumed tokens: 6946816000 | elapsed time per iteration (s): 0.75 | learning rate: 1.565E-04 | global batch size: 256 | lm loss: 2.280524E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.947 | TFLOPs: 20.63 | +31: iteration 13260/ 39672 | consumed samples: 3394560 | consumed tokens: 6952058880 | elapsed time per iteration (s): 0.76 | learning rate: 1.564E-04 | global batch size: 256 | lm loss: 2.288980E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.611 | TFLOPs: 20.30 | +31: iteration 13270/ 39672 | consumed samples: 3397120 | consumed tokens: 6957301760 | elapsed time per iteration (s): 0.76 | learning rate: 1.564E-04 | global batch size: 256 | lm loss: 2.286893E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.831 | TFLOPs: 20.38 | +31: iteration 13280/ 39672 | consumed samples: 3399680 | consumed tokens: 6962544640 | elapsed time per iteration (s): 0.75 | learning rate: 1.563E-04 | global batch size: 256 | lm loss: 2.240626E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.713 | TFLOPs: 20.73 | +31: iteration 13290/ 39672 | consumed samples: 3402240 | consumed tokens: 6967787520 | elapsed time per iteration (s): 0.76 | learning rate: 1.562E-04 | global batch size: 256 | lm loss: 2.283406E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.059 | TFLOPs: 20.51 | +31: iteration 13300/ 39672 | consumed samples: 3404800 | consumed tokens: 6973030400 | elapsed time per iteration (s): 0.84 | learning rate: 1.562E-04 | global batch size: 256 | lm loss: 2.272300E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.741 | TFLOPs: 18.44 | +31: iteration 13310/ 39672 | consumed samples: 3407360 | consumed tokens: 6978273280 | elapsed time per iteration (s): 0.80 | learning rate: 1.561E-04 | global batch size: 256 | lm loss: 2.273114E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.897 | TFLOPs: 19.41 | +31: iteration 13320/ 39672 | consumed samples: 3409920 | consumed tokens: 6983516160 | elapsed time per iteration (s): 0.85 | learning rate: 1.560E-04 | global batch size: 256 | lm loss: 2.256420E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.764 | TFLOPs: 18.32 | +31: iteration 13330/ 39672 | consumed samples: 3412480 | consumed tokens: 6988759040 | elapsed time per iteration (s): 0.81 | learning rate: 1.560E-04 | global batch size: 256 | lm loss: 2.255277E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.579 | TFLOPs: 19.09 | +31: iteration 13340/ 39672 | consumed samples: 3415040 | consumed tokens: 6994001920 | elapsed time per iteration (s): 0.78 | learning rate: 1.559E-04 | global batch size: 256 | lm loss: 2.255883E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.947 | TFLOPs: 19.96 | +31: iteration 13350/ 39672 | consumed samples: 3417600 | consumed tokens: 6999244800 | elapsed time per iteration (s): 0.73 | learning rate: 1.559E-04 | global batch size: 256 | lm loss: 2.251938E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.473 | TFLOPs: 21.20 | +31: iteration 13360/ 39672 | consumed samples: 3420160 | consumed tokens: 7004487680 | elapsed time per iteration (s): 0.74 | learning rate: 1.558E-04 | global batch size: 256 | lm loss: 2.261217E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.319 | TFLOPs: 20.95 | +31: iteration 13370/ 39672 | consumed samples: 3422720 | consumed tokens: 7009730560 | elapsed time per iteration (s): 0.72 | learning rate: 1.557E-04 | global batch size: 256 | lm loss: 2.258486E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.486 | TFLOPs: 21.51 | +31: iteration 13380/ 39672 | consumed samples: 3425280 | consumed tokens: 7014973440 | elapsed time per iteration (s): 0.71 | learning rate: 1.557E-04 | global batch size: 256 | lm loss: 2.254040E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.310 | TFLOPs: 21.74 | +31: iteration 13390/ 39672 | consumed samples: 3427840 | consumed tokens: 7020216320 | elapsed time per iteration (s): 0.76 | learning rate: 1.556E-04 | global batch size: 256 | lm loss: 2.261093E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.720 | TFLOPs: 20.25 | +31: iteration 13400/ 39672 | consumed samples: 3430400 | consumed tokens: 7025459200 | elapsed time per iteration (s): 0.80 | learning rate: 1.556E-04 | global batch size: 256 | lm loss: 2.262607E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.790 | TFLOPs: 19.41 | +31: iteration 13410/ 39672 | consumed samples: 3432960 | consumed tokens: 7030702080 | elapsed time per iteration (s): 0.81 | learning rate: 1.555E-04 | global batch size: 256 | lm loss: 2.285098E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.923 | TFLOPs: 19.17 | +31: iteration 13420/ 39672 | consumed samples: 3435520 | consumed tokens: 7035944960 | elapsed time per iteration (s): 0.77 | learning rate: 1.554E-04 | global batch size: 256 | lm loss: 2.294595E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.641 | TFLOPs: 20.18 | +31: iteration 13430/ 39672 | consumed samples: 3438080 | consumed tokens: 7041187840 | elapsed time per iteration (s): 0.76 | learning rate: 1.554E-04 | global batch size: 256 | lm loss: 2.241588E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.830 | TFLOPs: 20.26 | +31: iteration 13440/ 39672 | consumed samples: 3440640 | consumed tokens: 7046430720 | elapsed time per iteration (s): 0.77 | learning rate: 1.553E-04 | global batch size: 256 | lm loss: 2.254061E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.304 | TFLOPs: 20.04 | +31: iteration 13450/ 39672 | consumed samples: 3443200 | consumed tokens: 7051673600 | elapsed time per iteration (s): 0.75 | learning rate: 1.552E-04 | global batch size: 256 | lm loss: 2.265950E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.048 | TFLOPs: 20.63 | +31: iteration 13460/ 39672 | consumed samples: 3445760 | consumed tokens: 7056916480 | elapsed time per iteration (s): 0.74 | learning rate: 1.552E-04 | global batch size: 256 | lm loss: 2.279516E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.114 | TFLOPs: 21.00 | +31: iteration 13470/ 39672 | consumed samples: 3448320 | consumed tokens: 7062159360 | elapsed time per iteration (s): 0.74 | learning rate: 1.551E-04 | global batch size: 256 | lm loss: 2.229707E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.659 | TFLOPs: 21.03 | +31: iteration 13480/ 39672 | consumed samples: 3450880 | consumed tokens: 7067402240 | elapsed time per iteration (s): 0.77 | learning rate: 1.551E-04 | global batch size: 256 | lm loss: 2.249651E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.344 | TFLOPs: 19.98 | +31: iteration 13490/ 39672 | consumed samples: 3453440 | consumed tokens: 7072645120 | elapsed time per iteration (s): 0.78 | learning rate: 1.550E-04 | global batch size: 256 | lm loss: 2.240066E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.756 | TFLOPs: 19.95 | +31: iteration 13500/ 39672 | consumed samples: 3456000 | consumed tokens: 7077888000 | elapsed time per iteration (s): 0.76 | learning rate: 1.549E-04 | global batch size: 256 | lm loss: 2.232196E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.471 | TFLOPs: 20.36 | +31: iteration 13510/ 39672 | consumed samples: 3458560 | consumed tokens: 7083130880 | elapsed time per iteration (s): 0.80 | learning rate: 1.549E-04 | global batch size: 256 | lm loss: 2.271492E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.301 | TFLOPs: 19.44 | +31: iteration 13520/ 39672 | consumed samples: 3461120 | consumed tokens: 7088373760 | elapsed time per iteration (s): 0.73 | learning rate: 1.548E-04 | global batch size: 256 | lm loss: 2.273492E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.486 | TFLOPs: 21.32 | +31: iteration 13530/ 39672 | consumed samples: 3463680 | consumed tokens: 7093616640 | elapsed time per iteration (s): 0.78 | learning rate: 1.547E-04 | global batch size: 256 | lm loss: 2.242496E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.130 | TFLOPs: 19.73 | +31: iteration 13540/ 39672 | consumed samples: 3466240 | consumed tokens: 7098859520 | elapsed time per iteration (s): 0.75 | learning rate: 1.547E-04 | global batch size: 256 | lm loss: 2.278321E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.622 | TFLOPs: 20.55 | +31: iteration 13550/ 39672 | consumed samples: 3468800 | consumed tokens: 7104102400 | elapsed time per iteration (s): 0.73 | learning rate: 1.546E-04 | global batch size: 256 | lm loss: 2.258986E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.054 | TFLOPs: 21.12 | +31: iteration 13560/ 39672 | consumed samples: 3471360 | consumed tokens: 7109345280 | elapsed time per iteration (s): 0.76 | learning rate: 1.546E-04 | global batch size: 256 | lm loss: 2.247996E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.199 | TFLOPs: 20.40 | +31: iteration 13570/ 39672 | consumed samples: 3473920 | consumed tokens: 7114588160 | elapsed time per iteration (s): 0.79 | learning rate: 1.545E-04 | global batch size: 256 | lm loss: 2.265345E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.436 | TFLOPs: 19.63 | +31: iteration 13580/ 39672 | consumed samples: 3476480 | consumed tokens: 7119831040 | elapsed time per iteration (s): 0.77 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 2.253590E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.236 | TFLOPs: 20.10 | +31: iteration 13590/ 39672 | consumed samples: 3479040 | consumed tokens: 7125073920 | elapsed time per iteration (s): 0.80 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 2.242793E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.474 | TFLOPs: 19.27 | +31: iteration 13600/ 39672 | consumed samples: 3481600 | consumed tokens: 7130316800 | elapsed time per iteration (s): 0.78 | learning rate: 1.543E-04 | global batch size: 256 | lm loss: 2.292040E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.836 | TFLOPs: 19.77 | +31: iteration 13610/ 39672 | consumed samples: 3484160 | consumed tokens: 7135559680 | elapsed time per iteration (s): 0.82 | learning rate: 1.542E-04 | global batch size: 256 | lm loss: 2.258357E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.692 | TFLOPs: 18.80 | +31: iteration 13620/ 39672 | consumed samples: 3486720 | consumed tokens: 7140802560 | elapsed time per iteration (s): 0.81 | learning rate: 1.542E-04 | global batch size: 256 | lm loss: 2.239772E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.253 | TFLOPs: 19.19 | +31: iteration 13630/ 39672 | consumed samples: 3489280 | consumed tokens: 7146045440 | elapsed time per iteration (s): 0.80 | learning rate: 1.541E-04 | global batch size: 256 | lm loss: 2.258660E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.127 | TFLOPs: 19.31 | +31: iteration 13640/ 39672 | consumed samples: 3491840 | consumed tokens: 7151288320 | elapsed time per iteration (s): 0.81 | learning rate: 1.541E-04 | global batch size: 256 | lm loss: 2.232896E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.817 | TFLOPs: 19.17 | +31: iteration 13650/ 39672 | consumed samples: 3494400 | consumed tokens: 7156531200 | elapsed time per iteration (s): 0.78 | learning rate: 1.540E-04 | global batch size: 256 | lm loss: 2.269149E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.988 | TFLOPs: 19.78 | +31: iteration 13660/ 39672 | consumed samples: 3496960 | consumed tokens: 7161774080 | elapsed time per iteration (s): 0.76 | learning rate: 1.539E-04 | global batch size: 256 | lm loss: 2.248895E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.709 | TFLOPs: 20.31 | +31: iteration 13670/ 39672 | consumed samples: 3499520 | consumed tokens: 7167016960 | elapsed time per iteration (s): 0.75 | learning rate: 1.539E-04 | global batch size: 256 | lm loss: 2.273845E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.026 | TFLOPs: 20.57 | +31: iteration 13680/ 39672 | consumed samples: 3502080 | consumed tokens: 7172259840 | elapsed time per iteration (s): 0.75 | learning rate: 1.538E-04 | global batch size: 256 | lm loss: 2.240887E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.027 | TFLOPs: 20.75 | +31: iteration 13690/ 39672 | consumed samples: 3504640 | consumed tokens: 7177502720 | elapsed time per iteration (s): 0.73 | learning rate: 1.537E-04 | global batch size: 256 | lm loss: 2.262321E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.787 | TFLOPs: 21.22 | +31: iteration 13700/ 39672 | consumed samples: 3507200 | consumed tokens: 7182745600 | elapsed time per iteration (s): 0.74 | learning rate: 1.537E-04 | global batch size: 256 | lm loss: 2.280221E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.285 | TFLOPs: 21.01 | +31: iteration 13710/ 39672 | consumed samples: 3509760 | consumed tokens: 7187988480 | elapsed time per iteration (s): 0.77 | learning rate: 1.536E-04 | global batch size: 256 | lm loss: 2.249136E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.947 | TFLOPs: 20.08 | +31: iteration 13720/ 39672 | consumed samples: 3512320 | consumed tokens: 7193231360 | elapsed time per iteration (s): 0.74 | learning rate: 1.536E-04 | global batch size: 256 | lm loss: 2.227279E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.634 | TFLOPs: 20.97 | +31: iteration 13730/ 39672 | consumed samples: 3514880 | consumed tokens: 7198474240 | elapsed time per iteration (s): 0.75 | learning rate: 1.535E-04 | global batch size: 256 | lm loss: 2.257474E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.469 | TFLOPs: 20.72 | +31: iteration 13740/ 39672 | consumed samples: 3517440 | consumed tokens: 7203717120 | elapsed time per iteration (s): 0.81 | learning rate: 1.534E-04 | global batch size: 256 | lm loss: 2.263451E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.427 | TFLOPs: 19.20 | +31: iteration 13750/ 39672 | consumed samples: 3520000 | consumed tokens: 7208960000 | elapsed time per iteration (s): 0.78 | learning rate: 1.534E-04 | global batch size: 256 | lm loss: 2.257236E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.174 | TFLOPs: 19.85 | +31: iteration 13760/ 39672 | consumed samples: 3522560 | consumed tokens: 7214202880 | elapsed time per iteration (s): 0.83 | learning rate: 1.533E-04 | global batch size: 256 | lm loss: 2.228837E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.226 | TFLOPs: 18.77 | +31: iteration 13770/ 39672 | consumed samples: 3525120 | consumed tokens: 7219445760 | elapsed time per iteration (s): 0.78 | learning rate: 1.532E-04 | global batch size: 256 | lm loss: 2.288400E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.139 | TFLOPs: 19.85 | +31: iteration 13780/ 39672 | consumed samples: 3527680 | consumed tokens: 7224688640 | elapsed time per iteration (s): 0.83 | learning rate: 1.532E-04 | global batch size: 256 | lm loss: 2.231241E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.976 | TFLOPs: 18.63 | +31: iteration 13790/ 39672 | consumed samples: 3530240 | consumed tokens: 7229931520 | elapsed time per iteration (s): 0.81 | learning rate: 1.531E-04 | global batch size: 256 | lm loss: 2.262278E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.149 | TFLOPs: 19.19 | +31: iteration 13800/ 39672 | consumed samples: 3532800 | consumed tokens: 7235174400 | elapsed time per iteration (s): 0.77 | learning rate: 1.530E-04 | global batch size: 256 | lm loss: 2.265138E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.366 | TFLOPs: 20.05 | +31: iteration 13810/ 39672 | consumed samples: 3535360 | consumed tokens: 7240417280 | elapsed time per iteration (s): 0.75 | learning rate: 1.530E-04 | global batch size: 256 | lm loss: 2.232921E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.406 | TFLOPs: 20.65 | +31: iteration 13820/ 39672 | consumed samples: 3537920 | consumed tokens: 7245660160 | elapsed time per iteration (s): 0.75 | learning rate: 1.529E-04 | global batch size: 256 | lm loss: 2.243853E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.125 | TFLOPs: 20.64 | +31: iteration 13830/ 39672 | consumed samples: 3540480 | consumed tokens: 7250903040 | elapsed time per iteration (s): 0.74 | learning rate: 1.529E-04 | global batch size: 256 | lm loss: 2.266434E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.862 | TFLOPs: 20.86 | +31: iteration 13840/ 39672 | consumed samples: 3543040 | consumed tokens: 7256145920 | elapsed time per iteration (s): 0.77 | learning rate: 1.528E-04 | global batch size: 256 | lm loss: 2.237129E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.163 | TFLOPs: 20.09 | +31: iteration 13850/ 39672 | consumed samples: 3545600 | consumed tokens: 7261388800 | elapsed time per iteration (s): 0.74 | learning rate: 1.527E-04 | global batch size: 256 | lm loss: 2.260661E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.609 | TFLOPs: 21.03 | +31: iteration 13860/ 39672 | consumed samples: 3548160 | consumed tokens: 7266631680 | elapsed time per iteration (s): 0.75 | learning rate: 1.527E-04 | global batch size: 256 | lm loss: 2.293566E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.456 | TFLOPs: 20.60 | +31: iteration 13870/ 39672 | consumed samples: 3550720 | consumed tokens: 7271874560 | elapsed time per iteration (s): 0.74 | learning rate: 1.526E-04 | global batch size: 256 | lm loss: 2.259724E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.965 | TFLOPs: 20.93 | +31: iteration 13880/ 39672 | consumed samples: 3553280 | consumed tokens: 7277117440 | elapsed time per iteration (s): 0.74 | learning rate: 1.525E-04 | global batch size: 256 | lm loss: 2.218878E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.648 | TFLOPs: 20.85 | +31: iteration 13890/ 39672 | consumed samples: 3555840 | consumed tokens: 7282360320 | elapsed time per iteration (s): 0.77 | learning rate: 1.525E-04 | global batch size: 256 | lm loss: 2.243645E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.508 | TFLOPs: 19.99 | +31: iteration 13900/ 39672 | consumed samples: 3558400 | consumed tokens: 7287603200 | elapsed time per iteration (s): 0.75 | learning rate: 1.524E-04 | global batch size: 256 | lm loss: 2.228865E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.209 | TFLOPs: 20.76 | +31: iteration 13910/ 39672 | consumed samples: 3560960 | consumed tokens: 7292846080 | elapsed time per iteration (s): 0.74 | learning rate: 1.523E-04 | global batch size: 256 | lm loss: 2.265210E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.046 | TFLOPs: 21.06 | +31: iteration 13920/ 39672 | consumed samples: 3563520 | consumed tokens: 7298088960 | elapsed time per iteration (s): 0.83 | learning rate: 1.523E-04 | global batch size: 256 | lm loss: 2.234473E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.516 | TFLOPs: 18.72 | +31: iteration 13930/ 39672 | consumed samples: 3566080 | consumed tokens: 7303331840 | elapsed time per iteration (s): 0.73 | learning rate: 1.522E-04 | global batch size: 256 | lm loss: 2.247842E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.390 | TFLOPs: 21.08 | +31: iteration 13940/ 39672 | consumed samples: 3568640 | consumed tokens: 7308574720 | elapsed time per iteration (s): 0.79 | learning rate: 1.522E-04 | global batch size: 256 | lm loss: 2.269821E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.745 | TFLOPs: 19.65 | +31: iteration 13950/ 39672 | consumed samples: 3571200 | consumed tokens: 7313817600 | elapsed time per iteration (s): 0.73 | learning rate: 1.521E-04 | global batch size: 256 | lm loss: 2.264944E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.047 | TFLOPs: 21.18 | +31: iteration 13960/ 39672 | consumed samples: 3573760 | consumed tokens: 7319060480 | elapsed time per iteration (s): 0.80 | learning rate: 1.520E-04 | global batch size: 256 | lm loss: 2.249783E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.796 | TFLOPs: 19.41 | +31: iteration 13970/ 39672 | consumed samples: 3576320 | consumed tokens: 7324303360 | elapsed time per iteration (s): 0.72 | learning rate: 1.520E-04 | global batch size: 256 | lm loss: 2.237170E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.075 | TFLOPs: 21.60 | +31: iteration 13980/ 39672 | consumed samples: 3578880 | consumed tokens: 7329546240 | elapsed time per iteration (s): 0.77 | learning rate: 1.519E-04 | global batch size: 256 | lm loss: 2.250580E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.321 | TFLOPs: 20.10 | +31: iteration 13990/ 39672 | consumed samples: 3581440 | consumed tokens: 7334789120 | elapsed time per iteration (s): 0.79 | learning rate: 1.518E-04 | global batch size: 256 | lm loss: 2.220515E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.982 | TFLOPs: 19.72 | + 0: [2022-11-30 12:19:12,548] [INFO] [logging.py:68:log_dist] [Rank 0] step=14000, skipped=0, lr=[0.00015177606480374018, 0.00015177606480374018, 0.00015177606480374018], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 14000/ 39672 | consumed samples: 3584000 | consumed tokens: 7340032000 | elapsed time per iteration (s): 0.80 | learning rate: 1.518E-04 | global batch size: 256 | lm loss: 2.226457E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.861 | TFLOPs: 19.41 | + 0: steps: 14000 loss: 2.2440 iter time (s): 0.787 samples/sec: 325.170 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 14000 | lm loss value: 2.185590E+00 | lm loss PPL: 8.895894E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 14010/ 39672 | consumed samples: 3586560 | consumed tokens: 7345274880 | elapsed time per iteration (s): 0.84 | learning rate: 1.517E-04 | global batch size: 256 | lm loss: 2.282261E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.207 | TFLOPs: 18.52 | +31: iteration 14020/ 39672 | consumed samples: 3589120 | consumed tokens: 7350517760 | elapsed time per iteration (s): 0.76 | learning rate: 1.516E-04 | global batch size: 256 | lm loss: 2.260262E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.172 | TFLOPs: 20.40 | +31: iteration 14030/ 39672 | consumed samples: 3591680 | consumed tokens: 7355760640 | elapsed time per iteration (s): 0.84 | learning rate: 1.516E-04 | global batch size: 256 | lm loss: 2.265566E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.817 | TFLOPs: 18.38 | +31: iteration 14040/ 39672 | consumed samples: 3594240 | consumed tokens: 7361003520 | elapsed time per iteration (s): 0.76 | learning rate: 1.515E-04 | global batch size: 256 | lm loss: 2.238309E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.799 | TFLOPs: 20.44 | +31: iteration 14050/ 39672 | consumed samples: 3596800 | consumed tokens: 7366246400 | elapsed time per iteration (s): 0.77 | learning rate: 1.515E-04 | global batch size: 256 | lm loss: 2.227894E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.078 | TFLOPs: 20.09 | +31: iteration 14060/ 39672 | consumed samples: 3599360 | consumed tokens: 7371489280 | elapsed time per iteration (s): 0.74 | learning rate: 1.514E-04 | global batch size: 256 | lm loss: 2.229336E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.745 | TFLOPs: 20.80 | +31: iteration 14070/ 39672 | consumed samples: 3601920 | consumed tokens: 7376732160 | elapsed time per iteration (s): 0.75 | learning rate: 1.513E-04 | global batch size: 256 | lm loss: 2.211823E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.845 | TFLOPs: 20.74 | +31: iteration 14080/ 39672 | consumed samples: 3604480 | consumed tokens: 7381975040 | elapsed time per iteration (s): 0.76 | learning rate: 1.513E-04 | global batch size: 256 | lm loss: 2.259951E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.210 | TFLOPs: 20.46 | +31: iteration 14090/ 39672 | consumed samples: 3607040 | consumed tokens: 7387217920 | elapsed time per iteration (s): 0.75 | learning rate: 1.512E-04 | global batch size: 256 | lm loss: 2.222071E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.320 | TFLOPs: 20.53 | +31: iteration 14100/ 39672 | consumed samples: 3609600 | consumed tokens: 7392460800 | elapsed time per iteration (s): 0.75 | learning rate: 1.511E-04 | global batch size: 256 | lm loss: 2.251673E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.788 | TFLOPs: 20.74 | +31: iteration 14110/ 39672 | consumed samples: 3612160 | consumed tokens: 7397703680 | elapsed time per iteration (s): 0.77 | learning rate: 1.511E-04 | global batch size: 256 | lm loss: 2.253368E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.196 | TFLOPs: 20.16 | +31: iteration 14120/ 39672 | consumed samples: 3614720 | consumed tokens: 7402946560 | elapsed time per iteration (s): 0.73 | learning rate: 1.510E-04 | global batch size: 256 | lm loss: 2.252340E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.206 | TFLOPs: 21.31 | +31: iteration 14130/ 39672 | consumed samples: 3617280 | consumed tokens: 7408189440 | elapsed time per iteration (s): 0.78 | learning rate: 1.509E-04 | global batch size: 256 | lm loss: 2.270683E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.024 | TFLOPs: 19.97 | +31: iteration 14140/ 39672 | consumed samples: 3619840 | consumed tokens: 7413432320 | elapsed time per iteration (s): 0.75 | learning rate: 1.509E-04 | global batch size: 256 | lm loss: 2.224863E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.122 | TFLOPs: 20.58 | +31: iteration 14150/ 39672 | consumed samples: 3622400 | consumed tokens: 7418675200 | elapsed time per iteration (s): 0.73 | learning rate: 1.508E-04 | global batch size: 256 | lm loss: 2.265388E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.994 | TFLOPs: 21.17 | +31: iteration 14160/ 39672 | consumed samples: 3624960 | consumed tokens: 7423918080 | elapsed time per iteration (s): 0.77 | learning rate: 1.508E-04 | global batch size: 256 | lm loss: 2.276011E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.627 | TFLOPs: 20.18 | +31: iteration 14170/ 39672 | consumed samples: 3627520 | consumed tokens: 7429160960 | elapsed time per iteration (s): 0.74 | learning rate: 1.507E-04 | global batch size: 256 | lm loss: 2.237848E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.658 | TFLOPs: 20.97 | +31: iteration 14180/ 39672 | consumed samples: 3630080 | consumed tokens: 7434403840 | elapsed time per iteration (s): 0.73 | learning rate: 1.506E-04 | global batch size: 256 | lm loss: 2.281935E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.532 | TFLOPs: 21.15 | +31: iteration 14190/ 39672 | consumed samples: 3632640 | consumed tokens: 7439646720 | elapsed time per iteration (s): 0.72 | learning rate: 1.506E-04 | global batch size: 256 | lm loss: 2.243718E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.455 | TFLOPs: 21.38 | +31: iteration 14200/ 39672 | consumed samples: 3635200 | consumed tokens: 7444889600 | elapsed time per iteration (s): 0.74 | learning rate: 1.505E-04 | global batch size: 256 | lm loss: 2.247546E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.647 | TFLOPs: 21.03 | +31: iteration 14210/ 39672 | consumed samples: 3637760 | consumed tokens: 7450132480 | elapsed time per iteration (s): 0.74 | learning rate: 1.504E-04 | global batch size: 256 | lm loss: 2.223431E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.771 | TFLOPs: 20.80 | +31: iteration 14220/ 39672 | consumed samples: 3640320 | consumed tokens: 7455375360 | elapsed time per iteration (s): 0.75 | learning rate: 1.504E-04 | global batch size: 256 | lm loss: 2.257093E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.717 | TFLOPs: 20.61 | +31: iteration 14230/ 39672 | consumed samples: 3642880 | consumed tokens: 7460618240 | elapsed time per iteration (s): 0.74 | learning rate: 1.503E-04 | global batch size: 256 | lm loss: 2.238128E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.426 | TFLOPs: 20.84 | +31: iteration 14240/ 39672 | consumed samples: 3645440 | consumed tokens: 7465861120 | elapsed time per iteration (s): 0.72 | learning rate: 1.502E-04 | global batch size: 256 | lm loss: 2.257053E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.184 | TFLOPs: 21.37 | +31: iteration 14250/ 39672 | consumed samples: 3648000 | consumed tokens: 7471104000 | elapsed time per iteration (s): 0.73 | learning rate: 1.502E-04 | global batch size: 256 | lm loss: 2.254620E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.048 | TFLOPs: 21.24 | +31: iteration 14260/ 39672 | consumed samples: 3650560 | consumed tokens: 7476346880 | elapsed time per iteration (s): 0.73 | learning rate: 1.501E-04 | global batch size: 256 | lm loss: 2.267424E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.305 | TFLOPs: 21.25 | +31: iteration 14270/ 39672 | consumed samples: 3653120 | consumed tokens: 7481589760 | elapsed time per iteration (s): 0.76 | learning rate: 1.500E-04 | global batch size: 256 | lm loss: 2.224700E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.050 | TFLOPs: 20.27 | +31: iteration 14280/ 39672 | consumed samples: 3655680 | consumed tokens: 7486832640 | elapsed time per iteration (s): 0.74 | learning rate: 1.500E-04 | global batch size: 256 | lm loss: 2.239878E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.848 | TFLOPs: 21.04 | +31: iteration 14290/ 39672 | consumed samples: 3658240 | consumed tokens: 7492075520 | elapsed time per iteration (s): 0.77 | learning rate: 1.499E-04 | global batch size: 256 | lm loss: 2.255714E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.384 | TFLOPs: 20.05 | +31: iteration 14300/ 39672 | consumed samples: 3660800 | consumed tokens: 7497318400 | elapsed time per iteration (s): 0.73 | learning rate: 1.499E-04 | global batch size: 256 | lm loss: 2.202593E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.440 | TFLOPs: 21.20 | +31: iteration 14310/ 39672 | consumed samples: 3663360 | consumed tokens: 7502561280 | elapsed time per iteration (s): 0.74 | learning rate: 1.498E-04 | global batch size: 256 | lm loss: 2.205307E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.126 | TFLOPs: 20.82 | +31: iteration 14320/ 39672 | consumed samples: 3665920 | consumed tokens: 7507804160 | elapsed time per iteration (s): 0.76 | learning rate: 1.497E-04 | global batch size: 256 | lm loss: 2.210285E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.404 | TFLOPs: 20.35 | +31: iteration 14330/ 39672 | consumed samples: 3668480 | consumed tokens: 7513047040 | elapsed time per iteration (s): 0.78 | learning rate: 1.497E-04 | global batch size: 256 | lm loss: 2.224398E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.497 | TFLOPs: 19.87 | +31: iteration 14340/ 39672 | consumed samples: 3671040 | consumed tokens: 7518289920 | elapsed time per iteration (s): 0.76 | learning rate: 1.496E-04 | global batch size: 256 | lm loss: 2.243032E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.591 | TFLOPs: 20.42 | +31: iteration 14350/ 39672 | consumed samples: 3673600 | consumed tokens: 7523532800 | elapsed time per iteration (s): 0.76 | learning rate: 1.495E-04 | global batch size: 256 | lm loss: 2.265912E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.500 | TFLOPs: 20.36 | +31: iteration 14360/ 39672 | consumed samples: 3676160 | consumed tokens: 7528775680 | elapsed time per iteration (s): 0.78 | learning rate: 1.495E-04 | global batch size: 256 | lm loss: 2.270744E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.780 | TFLOPs: 19.83 | +31: iteration 14370/ 39672 | consumed samples: 3678720 | consumed tokens: 7534018560 | elapsed time per iteration (s): 0.73 | learning rate: 1.494E-04 | global batch size: 256 | lm loss: 2.269186E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.140 | TFLOPs: 21.12 | +31: iteration 14380/ 39672 | consumed samples: 3681280 | consumed tokens: 7539261440 | elapsed time per iteration (s): 0.75 | learning rate: 1.493E-04 | global batch size: 256 | lm loss: 2.226708E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.702 | TFLOPs: 20.61 | +31: iteration 14390/ 39672 | consumed samples: 3683840 | consumed tokens: 7544504320 | elapsed time per iteration (s): 0.76 | learning rate: 1.493E-04 | global batch size: 256 | lm loss: 2.251042E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.955 | TFLOPs: 20.51 | +31: iteration 14400/ 39672 | consumed samples: 3686400 | consumed tokens: 7549747200 | elapsed time per iteration (s): 0.76 | learning rate: 1.492E-04 | global batch size: 256 | lm loss: 2.205704E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.409 | TFLOPs: 20.41 | +31: iteration 14410/ 39672 | consumed samples: 3688960 | consumed tokens: 7554990080 | elapsed time per iteration (s): 0.75 | learning rate: 1.491E-04 | global batch size: 256 | lm loss: 2.204818E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.441 | TFLOPs: 20.54 | +31: iteration 14420/ 39672 | consumed samples: 3691520 | consumed tokens: 7560232960 | elapsed time per iteration (s): 0.80 | learning rate: 1.491E-04 | global batch size: 256 | lm loss: 2.234172E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.383 | TFLOPs: 19.32 | +31: iteration 14430/ 39672 | consumed samples: 3694080 | consumed tokens: 7565475840 | elapsed time per iteration (s): 0.78 | learning rate: 1.490E-04 | global batch size: 256 | lm loss: 2.244835E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.622 | TFLOPs: 19.76 | +31: iteration 14440/ 39672 | consumed samples: 3696640 | consumed tokens: 7570718720 | elapsed time per iteration (s): 0.81 | learning rate: 1.489E-04 | global batch size: 256 | lm loss: 2.208356E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.376 | TFLOPs: 19.20 | +31: iteration 14450/ 39672 | consumed samples: 3699200 | consumed tokens: 7575961600 | elapsed time per iteration (s): 0.79 | learning rate: 1.489E-04 | global batch size: 256 | lm loss: 2.226078E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.736 | TFLOPs: 19.52 | +31: iteration 14460/ 39672 | consumed samples: 3701760 | consumed tokens: 7581204480 | elapsed time per iteration (s): 0.79 | learning rate: 1.488E-04 | global batch size: 256 | lm loss: 2.252540E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.434 | TFLOPs: 19.57 | +31: iteration 14470/ 39672 | consumed samples: 3704320 | consumed tokens: 7586447360 | elapsed time per iteration (s): 0.83 | learning rate: 1.488E-04 | global batch size: 256 | lm loss: 2.257356E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.907 | TFLOPs: 18.63 | +31: iteration 14480/ 39672 | consumed samples: 3706880 | consumed tokens: 7591690240 | elapsed time per iteration (s): 0.82 | learning rate: 1.487E-04 | global batch size: 256 | lm loss: 2.220582E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.988 | TFLOPs: 18.81 | +31: iteration 14490/ 39672 | consumed samples: 3709440 | consumed tokens: 7596933120 | elapsed time per iteration (s): 0.81 | learning rate: 1.486E-04 | global batch size: 256 | lm loss: 2.218922E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.456 | TFLOPs: 19.14 | +31: iteration 14500/ 39672 | consumed samples: 3712000 | consumed tokens: 7602176000 | elapsed time per iteration (s): 0.80 | learning rate: 1.486E-04 | global batch size: 256 | lm loss: 2.237156E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.572 | TFLOPs: 19.45 | +31: iteration 14510/ 39672 | consumed samples: 3714560 | consumed tokens: 7607418880 | elapsed time per iteration (s): 0.84 | learning rate: 1.485E-04 | global batch size: 256 | lm loss: 2.252045E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.283 | TFLOPs: 18.35 | +31: iteration 14520/ 39672 | consumed samples: 3717120 | consumed tokens: 7612661760 | elapsed time per iteration (s): 0.78 | learning rate: 1.484E-04 | global batch size: 256 | lm loss: 2.290098E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.233 | TFLOPs: 19.74 | +31: iteration 14530/ 39672 | consumed samples: 3719680 | consumed tokens: 7617904640 | elapsed time per iteration (s): 0.82 | learning rate: 1.484E-04 | global batch size: 256 | lm loss: 2.233424E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.604 | TFLOPs: 18.91 | +31: iteration 14540/ 39672 | consumed samples: 3722240 | consumed tokens: 7623147520 | elapsed time per iteration (s): 0.83 | learning rate: 1.483E-04 | global batch size: 256 | lm loss: 2.245746E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.555 | TFLOPs: 18.61 | +31: iteration 14550/ 39672 | consumed samples: 3724800 | consumed tokens: 7628390400 | elapsed time per iteration (s): 0.81 | learning rate: 1.482E-04 | global batch size: 256 | lm loss: 2.212711E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.665 | TFLOPs: 19.04 | +31: iteration 14560/ 39672 | consumed samples: 3727360 | consumed tokens: 7633633280 | elapsed time per iteration (s): 0.78 | learning rate: 1.482E-04 | global batch size: 256 | lm loss: 2.228609E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.498 | TFLOPs: 19.81 | +31: iteration 14570/ 39672 | consumed samples: 3729920 | consumed tokens: 7638876160 | elapsed time per iteration (s): 0.87 | learning rate: 1.481E-04 | global batch size: 256 | lm loss: 2.230226E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 293.053 | TFLOPs: 17.73 | +31: iteration 14580/ 39672 | consumed samples: 3732480 | consumed tokens: 7644119040 | elapsed time per iteration (s): 0.93 | learning rate: 1.480E-04 | global batch size: 256 | lm loss: 2.209934E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 275.424 | TFLOPs: 16.66 | +31: iteration 14590/ 39672 | consumed samples: 3735040 | consumed tokens: 7649361920 | elapsed time per iteration (s): 0.87 | learning rate: 1.480E-04 | global batch size: 256 | lm loss: 2.248301E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 293.712 | TFLOPs: 17.77 | +31: iteration 14600/ 39672 | consumed samples: 3737600 | consumed tokens: 7654604800 | elapsed time per iteration (s): 0.83 | learning rate: 1.479E-04 | global batch size: 256 | lm loss: 2.259735E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.362 | TFLOPs: 18.72 | +31: iteration 14610/ 39672 | consumed samples: 3740160 | consumed tokens: 7659847680 | elapsed time per iteration (s): 0.88 | learning rate: 1.478E-04 | global batch size: 256 | lm loss: 2.240758E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 289.924 | TFLOPs: 17.54 | +31: iteration 14620/ 39672 | consumed samples: 3742720 | consumed tokens: 7665090560 | elapsed time per iteration (s): 0.79 | learning rate: 1.478E-04 | global batch size: 256 | lm loss: 2.252091E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.524 | TFLOPs: 19.63 | +31: iteration 14630/ 39672 | consumed samples: 3745280 | consumed tokens: 7670333440 | elapsed time per iteration (s): 0.80 | learning rate: 1.477E-04 | global batch size: 256 | lm loss: 2.211978E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.678 | TFLOPs: 19.28 | +31: iteration 14640/ 39672 | consumed samples: 3747840 | consumed tokens: 7675576320 | elapsed time per iteration (s): 0.75 | learning rate: 1.476E-04 | global batch size: 256 | lm loss: 2.222263E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.903 | TFLOPs: 20.62 | +31: iteration 14650/ 39672 | consumed samples: 3750400 | consumed tokens: 7680819200 | elapsed time per iteration (s): 0.72 | learning rate: 1.476E-04 | global batch size: 256 | lm loss: 2.241578E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.214 | TFLOPs: 21.37 | +31: iteration 14660/ 39672 | consumed samples: 3752960 | consumed tokens: 7686062080 | elapsed time per iteration (s): 0.80 | learning rate: 1.475E-04 | global batch size: 256 | lm loss: 2.216792E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.324 | TFLOPs: 19.44 | +31: iteration 14670/ 39672 | consumed samples: 3755520 | consumed tokens: 7691304960 | elapsed time per iteration (s): 0.75 | learning rate: 1.474E-04 | global batch size: 256 | lm loss: 2.228374E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.673 | TFLOPs: 20.55 | +31: iteration 14680/ 39672 | consumed samples: 3758080 | consumed tokens: 7696547840 | elapsed time per iteration (s): 0.86 | learning rate: 1.474E-04 | global batch size: 256 | lm loss: 2.249475E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.481 | TFLOPs: 18.06 | +31: iteration 14690/ 39672 | consumed samples: 3760640 | consumed tokens: 7701790720 | elapsed time per iteration (s): 0.80 | learning rate: 1.473E-04 | global batch size: 256 | lm loss: 2.220491E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.563 | TFLOPs: 19.33 | +31: iteration 14700/ 39672 | consumed samples: 3763200 | consumed tokens: 7707033600 | elapsed time per iteration (s): 0.86 | learning rate: 1.472E-04 | global batch size: 256 | lm loss: 2.252689E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.096 | TFLOPs: 17.97 | +31: iteration 14710/ 39672 | consumed samples: 3765760 | consumed tokens: 7712276480 | elapsed time per iteration (s): 0.83 | learning rate: 1.472E-04 | global batch size: 256 | lm loss: 2.224410E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.189 | TFLOPs: 18.64 | +31: iteration 14720/ 39672 | consumed samples: 3768320 | consumed tokens: 7717519360 | elapsed time per iteration (s): 0.80 | learning rate: 1.471E-04 | global batch size: 256 | lm loss: 2.239494E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.816 | TFLOPs: 19.41 | +31: iteration 14730/ 39672 | consumed samples: 3770880 | consumed tokens: 7722762240 | elapsed time per iteration (s): 0.85 | learning rate: 1.471E-04 | global batch size: 256 | lm loss: 2.240420E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.362 | TFLOPs: 18.17 | +31: iteration 14740/ 39672 | consumed samples: 3773440 | consumed tokens: 7728005120 | elapsed time per iteration (s): 0.83 | learning rate: 1.470E-04 | global batch size: 256 | lm loss: 2.237432E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.768 | TFLOPs: 18.62 | +31: iteration 14750/ 39672 | consumed samples: 3776000 | consumed tokens: 7733248000 | elapsed time per iteration (s): 0.85 | learning rate: 1.469E-04 | global batch size: 256 | lm loss: 2.241833E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.007 | TFLOPs: 18.21 | +31: iteration 14760/ 39672 | consumed samples: 3778560 | consumed tokens: 7738490880 | elapsed time per iteration (s): 1.00 | learning rate: 1.469E-04 | global batch size: 256 | lm loss: 2.217239E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 254.845 | TFLOPs: 15.42 | +31: iteration 14770/ 39672 | consumed samples: 3781120 | consumed tokens: 7743733760 | elapsed time per iteration (s): 0.82 | learning rate: 1.468E-04 | global batch size: 256 | lm loss: 2.225692E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.777 | TFLOPs: 18.80 | +31: iteration 14780/ 39672 | consumed samples: 3783680 | consumed tokens: 7748976640 | elapsed time per iteration (s): 0.94 | learning rate: 1.467E-04 | global batch size: 256 | lm loss: 2.257204E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 271.133 | TFLOPs: 16.40 | +31: iteration 14790/ 39672 | consumed samples: 3786240 | consumed tokens: 7754219520 | elapsed time per iteration (s): 0.89 | learning rate: 1.467E-04 | global batch size: 256 | lm loss: 2.249599E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 287.603 | TFLOPs: 17.40 | +31: iteration 14800/ 39672 | consumed samples: 3788800 | consumed tokens: 7759462400 | elapsed time per iteration (s): 0.79 | learning rate: 1.466E-04 | global batch size: 256 | lm loss: 2.222230E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.861 | TFLOPs: 19.65 | +31: iteration 14810/ 39672 | consumed samples: 3791360 | consumed tokens: 7764705280 | elapsed time per iteration (s): 0.83 | learning rate: 1.465E-04 | global batch size: 256 | lm loss: 2.262234E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.585 | TFLOPs: 18.73 | +31: iteration 14820/ 39672 | consumed samples: 3793920 | consumed tokens: 7769948160 | elapsed time per iteration (s): 0.87 | learning rate: 1.465E-04 | global batch size: 256 | lm loss: 2.212335E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.808 | TFLOPs: 17.90 | +31: iteration 14830/ 39672 | consumed samples: 3796480 | consumed tokens: 7775191040 | elapsed time per iteration (s): 0.82 | learning rate: 1.464E-04 | global batch size: 256 | lm loss: 2.239294E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.075 | TFLOPs: 18.88 | +31: iteration 14840/ 39672 | consumed samples: 3799040 | consumed tokens: 7780433920 | elapsed time per iteration (s): 0.80 | learning rate: 1.463E-04 | global batch size: 256 | lm loss: 2.222192E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.214 | TFLOPs: 19.37 | +31: iteration 14850/ 39672 | consumed samples: 3801600 | consumed tokens: 7785676800 | elapsed time per iteration (s): 0.82 | learning rate: 1.463E-04 | global batch size: 256 | lm loss: 2.220545E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.730 | TFLOPs: 18.92 | +31: iteration 14860/ 39672 | consumed samples: 3804160 | consumed tokens: 7790919680 | elapsed time per iteration (s): 0.84 | learning rate: 1.462E-04 | global batch size: 256 | lm loss: 2.211731E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.552 | TFLOPs: 18.49 | +31: iteration 14870/ 39672 | consumed samples: 3806720 | consumed tokens: 7796162560 | elapsed time per iteration (s): 0.84 | learning rate: 1.461E-04 | global batch size: 256 | lm loss: 2.253025E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.750 | TFLOPs: 18.38 | +31: iteration 14880/ 39672 | consumed samples: 3809280 | consumed tokens: 7801405440 | elapsed time per iteration (s): 0.80 | learning rate: 1.461E-04 | global batch size: 256 | lm loss: 2.222829E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.209 | TFLOPs: 19.25 | +31: iteration 14890/ 39672 | consumed samples: 3811840 | consumed tokens: 7806648320 | elapsed time per iteration (s): 0.83 | learning rate: 1.460E-04 | global batch size: 256 | lm loss: 2.209303E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.294 | TFLOPs: 18.59 | +31: iteration 14900/ 39672 | consumed samples: 3814400 | consumed tokens: 7811891200 | elapsed time per iteration (s): 0.79 | learning rate: 1.459E-04 | global batch size: 256 | lm loss: 2.209209E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.058 | TFLOPs: 19.48 | +31: iteration 14910/ 39672 | consumed samples: 3816960 | consumed tokens: 7817134080 | elapsed time per iteration (s): 0.82 | learning rate: 1.459E-04 | global batch size: 256 | lm loss: 2.247281E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.277 | TFLOPs: 18.95 | +31: iteration 14920/ 39672 | consumed samples: 3819520 | consumed tokens: 7822376960 | elapsed time per iteration (s): 0.82 | learning rate: 1.458E-04 | global batch size: 256 | lm loss: 2.209722E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.283 | TFLOPs: 18.95 | +31: iteration 14930/ 39672 | consumed samples: 3822080 | consumed tokens: 7827619840 | elapsed time per iteration (s): 0.86 | learning rate: 1.457E-04 | global batch size: 256 | lm loss: 2.214552E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.317 | TFLOPs: 18.05 | +31: iteration 14940/ 39672 | consumed samples: 3824640 | consumed tokens: 7832862720 | elapsed time per iteration (s): 0.79 | learning rate: 1.457E-04 | global batch size: 256 | lm loss: 2.235670E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.035 | TFLOPs: 19.54 | +31: iteration 14950/ 39672 | consumed samples: 3827200 | consumed tokens: 7838105600 | elapsed time per iteration (s): 0.81 | learning rate: 1.456E-04 | global batch size: 256 | lm loss: 2.209482E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.966 | TFLOPs: 19.24 | +31: iteration 14960/ 39672 | consumed samples: 3829760 | consumed tokens: 7843348480 | elapsed time per iteration (s): 0.81 | learning rate: 1.455E-04 | global batch size: 256 | lm loss: 2.186455E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.840 | TFLOPs: 19.11 | +31: iteration 14970/ 39672 | consumed samples: 3832320 | consumed tokens: 7848591360 | elapsed time per iteration (s): 0.80 | learning rate: 1.455E-04 | global batch size: 256 | lm loss: 2.223696E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.525 | TFLOPs: 19.33 | +31: iteration 14980/ 39672 | consumed samples: 3834880 | consumed tokens: 7853834240 | elapsed time per iteration (s): 0.82 | learning rate: 1.454E-04 | global batch size: 256 | lm loss: 2.231158E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.308 | TFLOPs: 18.77 | +31: iteration 14990/ 39672 | consumed samples: 3837440 | consumed tokens: 7859077120 | elapsed time per iteration (s): 0.80 | learning rate: 1.453E-04 | global batch size: 256 | lm loss: 2.273051E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.871 | TFLOPs: 19.41 | +31: iteration 15000/ 39672 | consumed samples: 3840000 | consumed tokens: 7864320000 | elapsed time per iteration (s): 0.81 | learning rate: 1.453E-04 | global batch size: 256 | lm loss: 2.219662E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.903 | TFLOPs: 19.17 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 15000 | lm loss value: 2.231841E+00 | lm loss PPL: 9.317006E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 15010/ 39672 | consumed samples: 3842560 | consumed tokens: 7869562880 | elapsed time per iteration (s): 0.79 | learning rate: 1.452E-04 | global batch size: 256 | lm loss: 2.234554E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.692 | TFLOPs: 19.58 | +31: iteration 15020/ 39672 | consumed samples: 3845120 | consumed tokens: 7874805760 | elapsed time per iteration (s): 0.81 | learning rate: 1.451E-04 | global batch size: 256 | lm loss: 2.216351E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.623 | TFLOPs: 19.22 | +31: iteration 15030/ 39672 | consumed samples: 3847680 | consumed tokens: 7880048640 | elapsed time per iteration (s): 0.81 | learning rate: 1.451E-04 | global batch size: 256 | lm loss: 2.243660E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.245 | TFLOPs: 19.07 | +31: iteration 15040/ 39672 | consumed samples: 3850240 | consumed tokens: 7885291520 | elapsed time per iteration (s): 0.80 | learning rate: 1.450E-04 | global batch size: 256 | lm loss: 2.267758E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.665 | TFLOPs: 19.34 | +31: iteration 15050/ 39672 | consumed samples: 3852800 | consumed tokens: 7890534400 | elapsed time per iteration (s): 0.81 | learning rate: 1.449E-04 | global batch size: 256 | lm loss: 2.209978E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.274 | TFLOPs: 19.19 | +31: iteration 15060/ 39672 | consumed samples: 3855360 | consumed tokens: 7895777280 | elapsed time per iteration (s): 0.90 | learning rate: 1.449E-04 | global batch size: 256 | lm loss: 2.209548E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 285.353 | TFLOPs: 17.26 | +31: iteration 15070/ 39672 | consumed samples: 3857920 | consumed tokens: 7901020160 | elapsed time per iteration (s): 0.84 | learning rate: 1.448E-04 | global batch size: 256 | lm loss: 2.226831E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.325 | TFLOPs: 18.53 | +31: iteration 15080/ 39672 | consumed samples: 3860480 | consumed tokens: 7906263040 | elapsed time per iteration (s): 0.83 | learning rate: 1.447E-04 | global batch size: 256 | lm loss: 2.212082E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.642 | TFLOPs: 18.61 | +31: iteration 15090/ 39672 | consumed samples: 3863040 | consumed tokens: 7911505920 | elapsed time per iteration (s): 0.82 | learning rate: 1.447E-04 | global batch size: 256 | lm loss: 2.215405E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.664 | TFLOPs: 18.98 | +31: iteration 15100/ 39672 | consumed samples: 3865600 | consumed tokens: 7916748800 | elapsed time per iteration (s): 0.83 | learning rate: 1.446E-04 | global batch size: 256 | lm loss: 2.215082E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.871 | TFLOPs: 18.56 | +31: iteration 15110/ 39672 | consumed samples: 3868160 | consumed tokens: 7921991680 | elapsed time per iteration (s): 0.83 | learning rate: 1.445E-04 | global batch size: 256 | lm loss: 2.237322E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.722 | TFLOPs: 18.68 | +31: iteration 15120/ 39672 | consumed samples: 3870720 | consumed tokens: 7927234560 | elapsed time per iteration (s): 0.80 | learning rate: 1.445E-04 | global batch size: 256 | lm loss: 2.224691E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.178 | TFLOPs: 19.37 | +31: iteration 15130/ 39672 | consumed samples: 3873280 | consumed tokens: 7932477440 | elapsed time per iteration (s): 0.81 | learning rate: 1.444E-04 | global batch size: 256 | lm loss: 2.208375E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.206 | TFLOPs: 19.19 | +31: iteration 15140/ 39672 | consumed samples: 3875840 | consumed tokens: 7937720320 | elapsed time per iteration (s): 0.82 | learning rate: 1.443E-04 | global batch size: 256 | lm loss: 2.250462E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.403 | TFLOPs: 18.84 | +31: iteration 15150/ 39672 | consumed samples: 3878400 | consumed tokens: 7942963200 | elapsed time per iteration (s): 0.83 | learning rate: 1.443E-04 | global batch size: 256 | lm loss: 2.206746E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.836 | TFLOPs: 18.68 | +31: iteration 15160/ 39672 | consumed samples: 3880960 | consumed tokens: 7948206080 | elapsed time per iteration (s): 0.79 | learning rate: 1.442E-04 | global batch size: 256 | lm loss: 2.222529E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.835 | TFLOPs: 19.59 | +31: iteration 15170/ 39672 | consumed samples: 3883520 | consumed tokens: 7953448960 | elapsed time per iteration (s): 0.85 | learning rate: 1.441E-04 | global batch size: 256 | lm loss: 2.241596E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.114 | TFLOPs: 18.28 | +31: iteration 15180/ 39672 | consumed samples: 3886080 | consumed tokens: 7958691840 | elapsed time per iteration (s): 0.81 | learning rate: 1.441E-04 | global batch size: 256 | lm loss: 2.217626E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.950 | TFLOPs: 19.11 | +31: iteration 15190/ 39672 | consumed samples: 3888640 | consumed tokens: 7963934720 | elapsed time per iteration (s): 0.79 | learning rate: 1.440E-04 | global batch size: 256 | lm loss: 2.220921E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.100 | TFLOPs: 19.73 | +31: iteration 15200/ 39672 | consumed samples: 3891200 | consumed tokens: 7969177600 | elapsed time per iteration (s): 0.81 | learning rate: 1.439E-04 | global batch size: 256 | lm loss: 2.243191E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.681 | TFLOPs: 19.22 | +31: iteration 15210/ 39672 | consumed samples: 3893760 | consumed tokens: 7974420480 | elapsed time per iteration (s): 0.77 | learning rate: 1.439E-04 | global batch size: 256 | lm loss: 2.219256E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.548 | TFLOPs: 20.06 | +31: iteration 15220/ 39672 | consumed samples: 3896320 | consumed tokens: 7979663360 | elapsed time per iteration (s): 0.81 | learning rate: 1.438E-04 | global batch size: 256 | lm loss: 2.245537E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.801 | TFLOPs: 19.11 | +31: iteration 15230/ 39672 | consumed samples: 3898880 | consumed tokens: 7984906240 | elapsed time per iteration (s): 0.82 | learning rate: 1.437E-04 | global batch size: 256 | lm loss: 2.225173E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.433 | TFLOPs: 18.96 | +31: iteration 15240/ 39672 | consumed samples: 3901440 | consumed tokens: 7990149120 | elapsed time per iteration (s): 0.85 | learning rate: 1.437E-04 | global batch size: 256 | lm loss: 2.234437E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.056 | TFLOPs: 18.27 | +31: iteration 15250/ 39672 | consumed samples: 3904000 | consumed tokens: 7995392000 | elapsed time per iteration (s): 0.82 | learning rate: 1.436E-04 | global batch size: 256 | lm loss: 2.216650E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.003 | TFLOPs: 18.94 | +31: iteration 15260/ 39672 | consumed samples: 3906560 | consumed tokens: 8000634880 | elapsed time per iteration (s): 0.81 | learning rate: 1.435E-04 | global batch size: 256 | lm loss: 2.240438E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.411 | TFLOPs: 19.02 | +31: iteration 15270/ 39672 | consumed samples: 3909120 | consumed tokens: 8005877760 | elapsed time per iteration (s): 0.85 | learning rate: 1.435E-04 | global batch size: 256 | lm loss: 2.218590E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.381 | TFLOPs: 18.17 | +31: iteration 15280/ 39672 | consumed samples: 3911680 | consumed tokens: 8011120640 | elapsed time per iteration (s): 0.81 | learning rate: 1.434E-04 | global batch size: 256 | lm loss: 2.237191E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.854 | TFLOPs: 19.23 | +31: iteration 15290/ 39672 | consumed samples: 3914240 | consumed tokens: 8016363520 | elapsed time per iteration (s): 0.83 | learning rate: 1.433E-04 | global batch size: 256 | lm loss: 2.212698E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.854 | TFLOPs: 18.62 | +31: iteration 15300/ 39672 | consumed samples: 3916800 | consumed tokens: 8021606400 | elapsed time per iteration (s): 0.88 | learning rate: 1.433E-04 | global batch size: 256 | lm loss: 2.215707E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 289.954 | TFLOPs: 17.54 | +31: iteration 15310/ 39672 | consumed samples: 3919360 | consumed tokens: 8026849280 | elapsed time per iteration (s): 0.81 | learning rate: 1.432E-04 | global batch size: 256 | lm loss: 2.231460E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.425 | TFLOPs: 19.14 | +31: iteration 15320/ 39672 | consumed samples: 3921920 | consumed tokens: 8032092160 | elapsed time per iteration (s): 0.83 | learning rate: 1.431E-04 | global batch size: 256 | lm loss: 2.222990E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.288 | TFLOPs: 18.65 | +31: iteration 15330/ 39672 | consumed samples: 3924480 | consumed tokens: 8037335040 | elapsed time per iteration (s): 0.78 | learning rate: 1.431E-04 | global batch size: 256 | lm loss: 2.210113E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.211 | TFLOPs: 19.80 | +31: iteration 15340/ 39672 | consumed samples: 3927040 | consumed tokens: 8042577920 | elapsed time per iteration (s): 0.83 | learning rate: 1.430E-04 | global batch size: 256 | lm loss: 2.238007E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.485 | TFLOPs: 18.66 | +31: iteration 15350/ 39672 | consumed samples: 3929600 | consumed tokens: 8047820800 | elapsed time per iteration (s): 0.81 | learning rate: 1.429E-04 | global batch size: 256 | lm loss: 2.222356E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.950 | TFLOPs: 19.11 | +31: iteration 15360/ 39672 | consumed samples: 3932160 | consumed tokens: 8053063680 | elapsed time per iteration (s): 0.82 | learning rate: 1.429E-04 | global batch size: 256 | lm loss: 2.227905E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.188 | TFLOPs: 18.95 | +31: iteration 15370/ 39672 | consumed samples: 3934720 | consumed tokens: 8058306560 | elapsed time per iteration (s): 0.80 | learning rate: 1.428E-04 | global batch size: 256 | lm loss: 2.235235E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.120 | TFLOPs: 19.43 | +31: iteration 15380/ 39672 | consumed samples: 3937280 | consumed tokens: 8063549440 | elapsed time per iteration (s): 0.83 | learning rate: 1.427E-04 | global batch size: 256 | lm loss: 2.202655E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.024 | TFLOPs: 18.70 | +31: iteration 15390/ 39672 | consumed samples: 3939840 | consumed tokens: 8068792320 | elapsed time per iteration (s): 0.80 | learning rate: 1.427E-04 | global batch size: 256 | lm loss: 2.240915E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.794 | TFLOPs: 19.47 | +31: iteration 15400/ 39672 | consumed samples: 3942400 | consumed tokens: 8074035200 | elapsed time per iteration (s): 0.83 | learning rate: 1.426E-04 | global batch size: 256 | lm loss: 2.210919E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.699 | TFLOPs: 18.55 | +31: iteration 15410/ 39672 | consumed samples: 3944960 | consumed tokens: 8079278080 | elapsed time per iteration (s): 0.79 | learning rate: 1.425E-04 | global batch size: 256 | lm loss: 2.252135E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.175 | TFLOPs: 19.67 | +31: iteration 15420/ 39672 | consumed samples: 3947520 | consumed tokens: 8084520960 | elapsed time per iteration (s): 0.81 | learning rate: 1.425E-04 | global batch size: 256 | lm loss: 2.245293E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.730 | TFLOPs: 19.16 | +31: iteration 15430/ 39672 | consumed samples: 3950080 | consumed tokens: 8089763840 | elapsed time per iteration (s): 0.72 | learning rate: 1.424E-04 | global batch size: 256 | lm loss: 2.221025E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.750 | TFLOPs: 21.64 | +31: iteration 15440/ 39672 | consumed samples: 3952640 | consumed tokens: 8095006720 | elapsed time per iteration (s): 0.79 | learning rate: 1.423E-04 | global batch size: 256 | lm loss: 2.219798E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.411 | TFLOPs: 19.57 | +31: iteration 15450/ 39672 | consumed samples: 3955200 | consumed tokens: 8100249600 | elapsed time per iteration (s): 0.76 | learning rate: 1.423E-04 | global batch size: 256 | lm loss: 2.232348E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.519 | TFLOPs: 20.48 | +31: iteration 15460/ 39672 | consumed samples: 3957760 | consumed tokens: 8105492480 | elapsed time per iteration (s): 0.73 | learning rate: 1.422E-04 | global batch size: 256 | lm loss: 2.230492E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.179 | TFLOPs: 21.18 | +31: iteration 15470/ 39672 | consumed samples: 3960320 | consumed tokens: 8110735360 | elapsed time per iteration (s): 0.78 | learning rate: 1.421E-04 | global batch size: 256 | lm loss: 2.229988E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.672 | TFLOPs: 19.82 | +31: iteration 15480/ 39672 | consumed samples: 3962880 | consumed tokens: 8115978240 | elapsed time per iteration (s): 0.81 | learning rate: 1.421E-04 | global batch size: 256 | lm loss: 2.232166E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.502 | TFLOPs: 19.03 | +31: iteration 15490/ 39672 | consumed samples: 3965440 | consumed tokens: 8121221120 | elapsed time per iteration (s): 0.81 | learning rate: 1.420E-04 | global batch size: 256 | lm loss: 2.221437E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.236 | TFLOPs: 19.01 | +31: iteration 15500/ 39672 | consumed samples: 3968000 | consumed tokens: 8126464000 | elapsed time per iteration (s): 0.80 | learning rate: 1.419E-04 | global batch size: 256 | lm loss: 2.225838E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.826 | TFLOPs: 19.29 | +31: iteration 15510/ 39672 | consumed samples: 3970560 | consumed tokens: 8131706880 | elapsed time per iteration (s): 0.84 | learning rate: 1.419E-04 | global batch size: 256 | lm loss: 2.234946E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.788 | TFLOPs: 18.38 | +31: iteration 15520/ 39672 | consumed samples: 3973120 | consumed tokens: 8136949760 | elapsed time per iteration (s): 0.84 | learning rate: 1.418E-04 | global batch size: 256 | lm loss: 2.227376E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.281 | TFLOPs: 18.47 | +31: iteration 15530/ 39672 | consumed samples: 3975680 | consumed tokens: 8142192640 | elapsed time per iteration (s): 0.80 | learning rate: 1.417E-04 | global batch size: 256 | lm loss: 2.246092E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.522 | TFLOPs: 19.33 | +31: iteration 15540/ 39672 | consumed samples: 3978240 | consumed tokens: 8147435520 | elapsed time per iteration (s): 0.88 | learning rate: 1.417E-04 | global batch size: 256 | lm loss: 2.236884E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 291.327 | TFLOPs: 17.62 | +31: iteration 15550/ 39672 | consumed samples: 3980800 | consumed tokens: 8152678400 | elapsed time per iteration (s): 0.84 | learning rate: 1.416E-04 | global batch size: 256 | lm loss: 2.201274E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.655 | TFLOPs: 18.49 | +31: iteration 15560/ 39672 | consumed samples: 3983360 | consumed tokens: 8157921280 | elapsed time per iteration (s): 0.79 | learning rate: 1.415E-04 | global batch size: 256 | lm loss: 2.226625E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.122 | TFLOPs: 19.61 | +31: iteration 15570/ 39672 | consumed samples: 3985920 | consumed tokens: 8163164160 | elapsed time per iteration (s): 0.75 | learning rate: 1.415E-04 | global batch size: 256 | lm loss: 2.214622E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.484 | TFLOPs: 20.60 | +31: iteration 15580/ 39672 | consumed samples: 3988480 | consumed tokens: 8168407040 | elapsed time per iteration (s): 0.79 | learning rate: 1.414E-04 | global batch size: 256 | lm loss: 2.220637E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.968 | TFLOPs: 19.72 | +31: iteration 15590/ 39672 | consumed samples: 3991040 | consumed tokens: 8173649920 | elapsed time per iteration (s): 0.79 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 2.245951E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.912 | TFLOPs: 19.66 | +31: iteration 15600/ 39672 | consumed samples: 3993600 | consumed tokens: 8178892800 | elapsed time per iteration (s): 0.75 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 2.226279E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.839 | TFLOPs: 20.74 | +31: iteration 15610/ 39672 | consumed samples: 3996160 | consumed tokens: 8184135680 | elapsed time per iteration (s): 0.77 | learning rate: 1.412E-04 | global batch size: 256 | lm loss: 2.238883E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.916 | TFLOPs: 20.20 | +31: iteration 15620/ 39672 | consumed samples: 3998720 | consumed tokens: 8189378560 | elapsed time per iteration (s): 0.77 | learning rate: 1.411E-04 | global batch size: 256 | lm loss: 2.203550E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.103 | TFLOPs: 20.03 | +31: iteration 15630/ 39672 | consumed samples: 4001280 | consumed tokens: 8194621440 | elapsed time per iteration (s): 0.77 | learning rate: 1.411E-04 | global batch size: 256 | lm loss: 2.235375E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.707 | TFLOPs: 20.01 | +31: iteration 15640/ 39672 | consumed samples: 4003840 | consumed tokens: 8199864320 | elapsed time per iteration (s): 0.75 | learning rate: 1.410E-04 | global batch size: 256 | lm loss: 2.228271E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.604 | TFLOPs: 20.73 | +31: iteration 15650/ 39672 | consumed samples: 4006400 | consumed tokens: 8205107200 | elapsed time per iteration (s): 0.74 | learning rate: 1.409E-04 | global batch size: 256 | lm loss: 2.260936E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.321 | TFLOPs: 20.89 | +31: iteration 15660/ 39672 | consumed samples: 4008960 | consumed tokens: 8210350080 | elapsed time per iteration (s): 0.81 | learning rate: 1.409E-04 | global batch size: 256 | lm loss: 2.196501E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.707 | TFLOPs: 19.22 | +31: iteration 15670/ 39672 | consumed samples: 4011520 | consumed tokens: 8215592960 | elapsed time per iteration (s): 0.85 | learning rate: 1.408E-04 | global batch size: 256 | lm loss: 2.222702E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.104 | TFLOPs: 18.16 | +31: iteration 15680/ 39672 | consumed samples: 4014080 | consumed tokens: 8220835840 | elapsed time per iteration (s): 0.87 | learning rate: 1.407E-04 | global batch size: 256 | lm loss: 2.209135E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 293.037 | TFLOPs: 17.73 | +31: iteration 15690/ 39672 | consumed samples: 4016640 | consumed tokens: 8226078720 | elapsed time per iteration (s): 0.84 | learning rate: 1.407E-04 | global batch size: 256 | lm loss: 2.247384E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.524 | TFLOPs: 18.36 | +31: iteration 15700/ 39672 | consumed samples: 4019200 | consumed tokens: 8231321600 | elapsed time per iteration (s): 0.83 | learning rate: 1.406E-04 | global batch size: 256 | lm loss: 2.227339E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.573 | TFLOPs: 18.73 | +31: iteration 15710/ 39672 | consumed samples: 4021760 | consumed tokens: 8236564480 | elapsed time per iteration (s): 0.83 | learning rate: 1.405E-04 | global batch size: 256 | lm loss: 2.236865E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.713 | TFLOPs: 18.74 | +31: iteration 15720/ 39672 | consumed samples: 4024320 | consumed tokens: 8241807360 | elapsed time per iteration (s): 0.83 | learning rate: 1.404E-04 | global batch size: 256 | lm loss: 2.244473E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.785 | TFLOPs: 18.74 | +31: iteration 15730/ 39672 | consumed samples: 4026880 | consumed tokens: 8247050240 | elapsed time per iteration (s): 0.84 | learning rate: 1.404E-04 | global batch size: 256 | lm loss: 2.234525E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.198 | TFLOPs: 18.40 | +31: iteration 15740/ 39672 | consumed samples: 4029440 | consumed tokens: 8252293120 | elapsed time per iteration (s): 0.82 | learning rate: 1.403E-04 | global batch size: 256 | lm loss: 2.229699E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.777 | TFLOPs: 18.86 | +31: iteration 15750/ 39672 | consumed samples: 4032000 | consumed tokens: 8257536000 | elapsed time per iteration (s): 0.80 | learning rate: 1.402E-04 | global batch size: 256 | lm loss: 2.221665E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.158 | TFLOPs: 19.25 | +31: iteration 15760/ 39672 | consumed samples: 4034560 | consumed tokens: 8262778880 | elapsed time per iteration (s): 0.77 | learning rate: 1.402E-04 | global batch size: 256 | lm loss: 2.233086E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.636 | TFLOPs: 20.24 | +31: iteration 15770/ 39672 | consumed samples: 4037120 | consumed tokens: 8268021760 | elapsed time per iteration (s): 0.74 | learning rate: 1.401E-04 | global batch size: 256 | lm loss: 2.229780E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.890 | TFLOPs: 20.80 | +31: iteration 15780/ 39672 | consumed samples: 4039680 | consumed tokens: 8273264640 | elapsed time per iteration (s): 0.73 | learning rate: 1.400E-04 | global batch size: 256 | lm loss: 2.207370E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.453 | TFLOPs: 21.08 | +31: iteration 15790/ 39672 | consumed samples: 4042240 | consumed tokens: 8278507520 | elapsed time per iteration (s): 0.78 | learning rate: 1.400E-04 | global batch size: 256 | lm loss: 2.206601E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.066 | TFLOPs: 19.97 | +31: iteration 15800/ 39672 | consumed samples: 4044800 | consumed tokens: 8283750400 | elapsed time per iteration (s): 0.74 | learning rate: 1.399E-04 | global batch size: 256 | lm loss: 2.203714E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.006 | TFLOPs: 20.87 | +31: iteration 15810/ 39672 | consumed samples: 4047360 | consumed tokens: 8288993280 | elapsed time per iteration (s): 0.74 | learning rate: 1.398E-04 | global batch size: 256 | lm loss: 2.187911E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.270 | TFLOPs: 20.83 | +31: iteration 15820/ 39672 | consumed samples: 4049920 | consumed tokens: 8294236160 | elapsed time per iteration (s): 0.79 | learning rate: 1.398E-04 | global batch size: 256 | lm loss: 2.243510E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.999 | TFLOPs: 19.54 | +31: iteration 15830/ 39672 | consumed samples: 4052480 | consumed tokens: 8299479040 | elapsed time per iteration (s): 0.74 | learning rate: 1.397E-04 | global batch size: 256 | lm loss: 2.223522E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.669 | TFLOPs: 20.91 | +31: iteration 15840/ 39672 | consumed samples: 4055040 | consumed tokens: 8304721920 | elapsed time per iteration (s): 0.76 | learning rate: 1.396E-04 | global batch size: 256 | lm loss: 2.237177E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.791 | TFLOPs: 20.44 | +31: iteration 15850/ 39672 | consumed samples: 4057600 | consumed tokens: 8309964800 | elapsed time per iteration (s): 0.74 | learning rate: 1.396E-04 | global batch size: 256 | lm loss: 2.235194E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.640 | TFLOPs: 20.91 | +31: iteration 15860/ 39672 | consumed samples: 4060160 | consumed tokens: 8315207680 | elapsed time per iteration (s): 0.87 | learning rate: 1.395E-04 | global batch size: 256 | lm loss: 2.218954E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 294.967 | TFLOPs: 17.84 | +31: iteration 15870/ 39672 | consumed samples: 4062720 | consumed tokens: 8320450560 | elapsed time per iteration (s): 0.76 | learning rate: 1.394E-04 | global batch size: 256 | lm loss: 2.202567E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.215 | TFLOPs: 20.34 | +31: iteration 15880/ 39672 | consumed samples: 4065280 | consumed tokens: 8325693440 | elapsed time per iteration (s): 0.74 | learning rate: 1.394E-04 | global batch size: 256 | lm loss: 2.213974E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.015 | TFLOPs: 20.93 | +31: iteration 15890/ 39672 | consumed samples: 4067840 | consumed tokens: 8330936320 | elapsed time per iteration (s): 0.81 | learning rate: 1.393E-04 | global batch size: 256 | lm loss: 2.221554E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.565 | TFLOPs: 19.09 | +31: iteration 15900/ 39672 | consumed samples: 4070400 | consumed tokens: 8336179200 | elapsed time per iteration (s): 0.74 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 2.229749E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.133 | TFLOPs: 20.94 | +31: iteration 15910/ 39672 | consumed samples: 4072960 | consumed tokens: 8341422080 | elapsed time per iteration (s): 0.75 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 2.231545E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.188 | TFLOPs: 20.52 | +31: iteration 15920/ 39672 | consumed samples: 4075520 | consumed tokens: 8346664960 | elapsed time per iteration (s): 0.76 | learning rate: 1.391E-04 | global batch size: 256 | lm loss: 2.187466E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.478 | TFLOPs: 20.30 | +31: iteration 15930/ 39672 | consumed samples: 4078080 | consumed tokens: 8351907840 | elapsed time per iteration (s): 0.73 | learning rate: 1.390E-04 | global batch size: 256 | lm loss: 2.211735E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.505 | TFLOPs: 21.27 | +31: iteration 15940/ 39672 | consumed samples: 4080640 | consumed tokens: 8357150720 | elapsed time per iteration (s): 0.74 | learning rate: 1.390E-04 | global batch size: 256 | lm loss: 2.217893E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.468 | TFLOPs: 20.96 | +31: iteration 15950/ 39672 | consumed samples: 4083200 | consumed tokens: 8362393600 | elapsed time per iteration (s): 0.74 | learning rate: 1.389E-04 | global batch size: 256 | lm loss: 2.229209E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.865 | TFLOPs: 20.98 | +31: iteration 15960/ 39672 | consumed samples: 4085760 | consumed tokens: 8367636480 | elapsed time per iteration (s): 0.78 | learning rate: 1.388E-04 | global batch size: 256 | lm loss: 2.207343E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.020 | TFLOPs: 19.84 | +31: iteration 15970/ 39672 | consumed samples: 4088320 | consumed tokens: 8372879360 | elapsed time per iteration (s): 0.80 | learning rate: 1.387E-04 | global batch size: 256 | lm loss: 2.222540E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.530 | TFLOPs: 19.33 | +31: iteration 15980/ 39672 | consumed samples: 4090880 | consumed tokens: 8378122240 | elapsed time per iteration (s): 0.72 | learning rate: 1.387E-04 | global batch size: 256 | lm loss: 2.242662E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.538 | TFLOPs: 21.39 | +31: iteration 15990/ 39672 | consumed samples: 4093440 | consumed tokens: 8383365120 | elapsed time per iteration (s): 0.76 | learning rate: 1.386E-04 | global batch size: 256 | lm loss: 2.234192E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.033 | TFLOPs: 20.45 | + 0: [2022-11-30 12:45:45,353] [INFO] [logging.py:68:log_dist] [Rank 0] step=16000, skipped=0, lr=[0.000138544301423559, 0.000138544301423559, 0.000138544301423559], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 16000/ 39672 | consumed samples: 4096000 | consumed tokens: 8388608000 | elapsed time per iteration (s): 0.74 | learning rate: 1.385E-04 | global batch size: 256 | lm loss: 2.221052E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.367 | TFLOPs: 21.01 | + 0: steps: 16000 loss: 2.3211 iter time (s): 0.792 samples/sec: 323.107 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 16000 | lm loss value: 2.115408E+00 | lm loss PPL: 8.292968E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 16010/ 39672 | consumed samples: 4098560 | consumed tokens: 8393850880 | elapsed time per iteration (s): 0.75 | learning rate: 1.385E-04 | global batch size: 256 | lm loss: 2.213063E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.034 | TFLOPs: 20.69 | +31: iteration 16020/ 39672 | consumed samples: 4101120 | consumed tokens: 8399093760 | elapsed time per iteration (s): 0.78 | learning rate: 1.384E-04 | global batch size: 256 | lm loss: 2.217131E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.959 | TFLOPs: 19.90 | +31: iteration 16030/ 39672 | consumed samples: 4103680 | consumed tokens: 8404336640 | elapsed time per iteration (s): 0.77 | learning rate: 1.383E-04 | global batch size: 256 | lm loss: 2.207515E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.950 | TFLOPs: 20.14 | +31: iteration 16040/ 39672 | consumed samples: 4106240 | consumed tokens: 8409579520 | elapsed time per iteration (s): 0.78 | learning rate: 1.383E-04 | global batch size: 256 | lm loss: 2.245546E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.479 | TFLOPs: 19.81 | +31: iteration 16050/ 39672 | consumed samples: 4108800 | consumed tokens: 8414822400 | elapsed time per iteration (s): 0.83 | learning rate: 1.382E-04 | global batch size: 256 | lm loss: 2.187134E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.236 | TFLOPs: 18.77 | +31: iteration 16060/ 39672 | consumed samples: 4111360 | consumed tokens: 8420065280 | elapsed time per iteration (s): 0.75 | learning rate: 1.381E-04 | global batch size: 256 | lm loss: 2.252611E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.161 | TFLOPs: 20.52 | +31: iteration 16070/ 39672 | consumed samples: 4113920 | consumed tokens: 8425308160 | elapsed time per iteration (s): 0.79 | learning rate: 1.381E-04 | global batch size: 256 | lm loss: 2.219229E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.824 | TFLOPs: 19.53 | +31: iteration 16080/ 39672 | consumed samples: 4116480 | consumed tokens: 8430551040 | elapsed time per iteration (s): 0.74 | learning rate: 1.380E-04 | global batch size: 256 | lm loss: 2.212976E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.327 | TFLOPs: 21.01 | +31: iteration 16090/ 39672 | consumed samples: 4119040 | consumed tokens: 8435793920 | elapsed time per iteration (s): 0.78 | learning rate: 1.379E-04 | global batch size: 256 | lm loss: 2.215956E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.168 | TFLOPs: 19.73 | +31: iteration 16100/ 39672 | consumed samples: 4121600 | consumed tokens: 8441036800 | elapsed time per iteration (s): 0.80 | learning rate: 1.379E-04 | global batch size: 256 | lm loss: 2.198253E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.370 | TFLOPs: 19.32 | +31: iteration 16110/ 39672 | consumed samples: 4124160 | consumed tokens: 8446279680 | elapsed time per iteration (s): 0.82 | learning rate: 1.378E-04 | global batch size: 256 | lm loss: 2.229922E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.537 | TFLOPs: 18.79 | +31: iteration 16120/ 39672 | consumed samples: 4126720 | consumed tokens: 8451522560 | elapsed time per iteration (s): 0.80 | learning rate: 1.377E-04 | global batch size: 256 | lm loss: 2.239364E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.148 | TFLOPs: 19.31 | +31: iteration 16130/ 39672 | consumed samples: 4129280 | consumed tokens: 8456765440 | elapsed time per iteration (s): 0.73 | learning rate: 1.377E-04 | global batch size: 256 | lm loss: 2.207642E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.427 | TFLOPs: 21.08 | +31: iteration 16140/ 39672 | consumed samples: 4131840 | consumed tokens: 8462008320 | elapsed time per iteration (s): 0.78 | learning rate: 1.376E-04 | global batch size: 256 | lm loss: 2.196952E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.837 | TFLOPs: 19.83 | +31: iteration 16150/ 39672 | consumed samples: 4134400 | consumed tokens: 8467251200 | elapsed time per iteration (s): 0.75 | learning rate: 1.375E-04 | global batch size: 256 | lm loss: 2.227613E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.749 | TFLOPs: 20.55 | +31: iteration 16160/ 39672 | consumed samples: 4136960 | consumed tokens: 8472494080 | elapsed time per iteration (s): 0.79 | learning rate: 1.374E-04 | global batch size: 256 | lm loss: 2.219633E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.575 | TFLOPs: 19.70 | +31: iteration 16170/ 39672 | consumed samples: 4139520 | consumed tokens: 8477736960 | elapsed time per iteration (s): 0.73 | learning rate: 1.374E-04 | global batch size: 256 | lm loss: 2.204868E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.654 | TFLOPs: 21.21 | +31: iteration 16180/ 39672 | consumed samples: 4142080 | consumed tokens: 8482979840 | elapsed time per iteration (s): 0.74 | learning rate: 1.373E-04 | global batch size: 256 | lm loss: 2.231779E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.853 | TFLOPs: 20.86 | +31: iteration 16190/ 39672 | consumed samples: 4144640 | consumed tokens: 8488222720 | elapsed time per iteration (s): 0.74 | learning rate: 1.372E-04 | global batch size: 256 | lm loss: 2.196433E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.787 | TFLOPs: 20.86 | +31: iteration 16200/ 39672 | consumed samples: 4147200 | consumed tokens: 8493465600 | elapsed time per iteration (s): 0.74 | learning rate: 1.372E-04 | global batch size: 256 | lm loss: 2.211090E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.010 | TFLOPs: 20.81 | +31: iteration 16210/ 39672 | consumed samples: 4149760 | consumed tokens: 8498708480 | elapsed time per iteration (s): 0.85 | learning rate: 1.371E-04 | global batch size: 256 | lm loss: 2.211810E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.707 | TFLOPs: 18.19 | +31: iteration 16220/ 39672 | consumed samples: 4152320 | consumed tokens: 8503951360 | elapsed time per iteration (s): 0.78 | learning rate: 1.370E-04 | global batch size: 256 | lm loss: 2.196596E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.800 | TFLOPs: 19.77 | +31: iteration 16230/ 39672 | consumed samples: 4154880 | consumed tokens: 8509194240 | elapsed time per iteration (s): 0.81 | learning rate: 1.370E-04 | global batch size: 256 | lm loss: 2.210705E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.827 | TFLOPs: 19.05 | +31: iteration 16240/ 39672 | consumed samples: 4157440 | consumed tokens: 8514437120 | elapsed time per iteration (s): 0.75 | learning rate: 1.369E-04 | global batch size: 256 | lm loss: 2.200367E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.810 | TFLOPs: 20.62 | +31: iteration 16250/ 39672 | consumed samples: 4160000 | consumed tokens: 8519680000 | elapsed time per iteration (s): 0.79 | learning rate: 1.368E-04 | global batch size: 256 | lm loss: 2.225122E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.546 | TFLOPs: 19.63 | +31: iteration 16260/ 39672 | consumed samples: 4162560 | consumed tokens: 8524922880 | elapsed time per iteration (s): 0.77 | learning rate: 1.368E-04 | global batch size: 256 | lm loss: 2.203449E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.001 | TFLOPs: 20.15 | +31: iteration 16270/ 39672 | consumed samples: 4165120 | consumed tokens: 8530165760 | elapsed time per iteration (s): 0.74 | learning rate: 1.367E-04 | global batch size: 256 | lm loss: 2.195117E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.972 | TFLOPs: 21.05 | +31: iteration 16280/ 39672 | consumed samples: 4167680 | consumed tokens: 8535408640 | elapsed time per iteration (s): 0.75 | learning rate: 1.366E-04 | global batch size: 256 | lm loss: 2.208479E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.120 | TFLOPs: 20.64 | +31: iteration 16290/ 39672 | consumed samples: 4170240 | consumed tokens: 8540651520 | elapsed time per iteration (s): 0.77 | learning rate: 1.366E-04 | global batch size: 256 | lm loss: 2.221438E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.059 | TFLOPs: 20.21 | +31: iteration 16300/ 39672 | consumed samples: 4172800 | consumed tokens: 8545894400 | elapsed time per iteration (s): 0.79 | learning rate: 1.365E-04 | global batch size: 256 | lm loss: 2.204523E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.267 | TFLOPs: 19.68 | +31: iteration 16310/ 39672 | consumed samples: 4175360 | consumed tokens: 8551137280 | elapsed time per iteration (s): 0.78 | learning rate: 1.364E-04 | global batch size: 256 | lm loss: 2.411938E+00 | grad norm: 8.495 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.301 | TFLOPs: 19.80 | +31: iteration 16320/ 39672 | consumed samples: 4177920 | consumed tokens: 8556380160 | elapsed time per iteration (s): 0.83 | learning rate: 1.364E-04 | global batch size: 256 | lm loss: 2.505652E+00 | grad norm: 0.712 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.742 | TFLOPs: 18.56 | +31: iteration 16330/ 39672 | consumed samples: 4180480 | consumed tokens: 8561623040 | elapsed time per iteration (s): 0.75 | learning rate: 1.363E-04 | global batch size: 256 | lm loss: 2.281795E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.804 | TFLOPs: 20.68 | +31: iteration 16340/ 39672 | consumed samples: 4183040 | consumed tokens: 8566865920 | elapsed time per iteration (s): 0.76 | learning rate: 1.362E-04 | global batch size: 256 | lm loss: 2.258109E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.459 | TFLOPs: 20.48 | +31: iteration 16350/ 39672 | consumed samples: 4185600 | consumed tokens: 8572108800 | elapsed time per iteration (s): 0.78 | learning rate: 1.361E-04 | global batch size: 256 | lm loss: 2.228981E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.470 | TFLOPs: 19.87 | +31: iteration 16360/ 39672 | consumed samples: 4188160 | consumed tokens: 8577351680 | elapsed time per iteration (s): 0.77 | learning rate: 1.361E-04 | global batch size: 256 | lm loss: 2.240989E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.469 | TFLOPs: 20.05 | +31: iteration 16370/ 39672 | consumed samples: 4190720 | consumed tokens: 8582594560 | elapsed time per iteration (s): 0.84 | learning rate: 1.360E-04 | global batch size: 256 | lm loss: 2.242419E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.800 | TFLOPs: 18.44 | +31: iteration 16380/ 39672 | consumed samples: 4193280 | consumed tokens: 8587837440 | elapsed time per iteration (s): 0.73 | learning rate: 1.359E-04 | global batch size: 256 | lm loss: 2.240576E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.526 | TFLOPs: 21.27 | +31: iteration 16390/ 39672 | consumed samples: 4195840 | consumed tokens: 8593080320 | elapsed time per iteration (s): 0.76 | learning rate: 1.359E-04 | global batch size: 256 | lm loss: 2.227332E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.906 | TFLOPs: 20.50 | +31: iteration 16400/ 39672 | consumed samples: 4198400 | consumed tokens: 8598323200 | elapsed time per iteration (s): 0.81 | learning rate: 1.358E-04 | global batch size: 256 | lm loss: 2.231101E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.912 | TFLOPs: 19.11 | +31: iteration 16410/ 39672 | consumed samples: 4200960 | consumed tokens: 8603566080 | elapsed time per iteration (s): 0.80 | learning rate: 1.357E-04 | global batch size: 256 | lm loss: 2.213099E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.780 | TFLOPs: 19.35 | +31: iteration 16420/ 39672 | consumed samples: 4203520 | consumed tokens: 8608808960 | elapsed time per iteration (s): 0.81 | learning rate: 1.357E-04 | global batch size: 256 | lm loss: 2.209882E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.559 | TFLOPs: 19.09 | +31: iteration 16430/ 39672 | consumed samples: 4206080 | consumed tokens: 8614051840 | elapsed time per iteration (s): 0.80 | learning rate: 1.356E-04 | global batch size: 256 | lm loss: 2.222836E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.305 | TFLOPs: 19.38 | +31: iteration 16440/ 39672 | consumed samples: 4208640 | consumed tokens: 8619294720 | elapsed time per iteration (s): 0.76 | learning rate: 1.355E-04 | global batch size: 256 | lm loss: 2.212087E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.808 | TFLOPs: 20.26 | +31: iteration 16450/ 39672 | consumed samples: 4211200 | consumed tokens: 8624537600 | elapsed time per iteration (s): 0.76 | learning rate: 1.355E-04 | global batch size: 256 | lm loss: 2.202741E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.724 | TFLOPs: 20.49 | +31: iteration 16460/ 39672 | consumed samples: 4213760 | consumed tokens: 8629780480 | elapsed time per iteration (s): 0.81 | learning rate: 1.354E-04 | global batch size: 256 | lm loss: 2.207093E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.572 | TFLOPs: 19.15 | +31: iteration 16470/ 39672 | consumed samples: 4216320 | consumed tokens: 8635023360 | elapsed time per iteration (s): 0.77 | learning rate: 1.353E-04 | global batch size: 256 | lm loss: 2.219987E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.337 | TFLOPs: 19.98 | +31: iteration 16480/ 39672 | consumed samples: 4218880 | consumed tokens: 8640266240 | elapsed time per iteration (s): 0.76 | learning rate: 1.352E-04 | global batch size: 256 | lm loss: 2.236540E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.603 | TFLOPs: 20.48 | +31: iteration 16490/ 39672 | consumed samples: 4221440 | consumed tokens: 8645509120 | elapsed time per iteration (s): 0.73 | learning rate: 1.352E-04 | global batch size: 256 | lm loss: 2.202760E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.166 | TFLOPs: 21.31 | +31: iteration 16500/ 39672 | consumed samples: 4224000 | consumed tokens: 8650752000 | elapsed time per iteration (s): 0.75 | learning rate: 1.351E-04 | global batch size: 256 | lm loss: 2.228255E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.012 | TFLOPs: 20.57 | +31: iteration 16510/ 39672 | consumed samples: 4226560 | consumed tokens: 8655994880 | elapsed time per iteration (s): 0.74 | learning rate: 1.350E-04 | global batch size: 256 | lm loss: 2.207290E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.129 | TFLOPs: 21.06 | +31: iteration 16520/ 39672 | consumed samples: 4229120 | consumed tokens: 8661237760 | elapsed time per iteration (s): 0.78 | learning rate: 1.350E-04 | global batch size: 256 | lm loss: 2.224241E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.388 | TFLOPs: 19.93 | +31: iteration 16530/ 39672 | consumed samples: 4231680 | consumed tokens: 8666480640 | elapsed time per iteration (s): 0.78 | learning rate: 1.349E-04 | global batch size: 256 | lm loss: 2.218132E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.546 | TFLOPs: 19.88 | +31: iteration 16540/ 39672 | consumed samples: 4234240 | consumed tokens: 8671723520 | elapsed time per iteration (s): 0.76 | learning rate: 1.348E-04 | global batch size: 256 | lm loss: 2.207591E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.777 | TFLOPs: 20.43 | +31: iteration 16550/ 39672 | consumed samples: 4236800 | consumed tokens: 8676966400 | elapsed time per iteration (s): 0.78 | learning rate: 1.348E-04 | global batch size: 256 | lm loss: 2.227855E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.013 | TFLOPs: 19.84 | +31: iteration 16560/ 39672 | consumed samples: 4239360 | consumed tokens: 8682209280 | elapsed time per iteration (s): 0.74 | learning rate: 1.347E-04 | global batch size: 256 | lm loss: 2.188476E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.255 | TFLOPs: 20.95 | +31: iteration 16570/ 39672 | consumed samples: 4241920 | consumed tokens: 8687452160 | elapsed time per iteration (s): 0.76 | learning rate: 1.346E-04 | global batch size: 256 | lm loss: 2.193209E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.860 | TFLOPs: 20.32 | +31: iteration 16580/ 39672 | consumed samples: 4244480 | consumed tokens: 8692695040 | elapsed time per iteration (s): 0.76 | learning rate: 1.346E-04 | global batch size: 256 | lm loss: 2.227723E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.447 | TFLOPs: 20.35 | +31: iteration 16590/ 39672 | consumed samples: 4247040 | consumed tokens: 8697937920 | elapsed time per iteration (s): 0.78 | learning rate: 1.345E-04 | global batch size: 256 | lm loss: 2.230674E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.656 | TFLOPs: 19.82 | +31: iteration 16600/ 39672 | consumed samples: 4249600 | consumed tokens: 8703180800 | elapsed time per iteration (s): 0.77 | learning rate: 1.344E-04 | global batch size: 256 | lm loss: 2.178491E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.100 | TFLOPs: 20.09 | +31: iteration 16610/ 39672 | consumed samples: 4252160 | consumed tokens: 8708423680 | elapsed time per iteration (s): 0.75 | learning rate: 1.343E-04 | global batch size: 256 | lm loss: 2.233731E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.022 | TFLOPs: 20.63 | +31: iteration 16620/ 39672 | consumed samples: 4254720 | consumed tokens: 8713666560 | elapsed time per iteration (s): 0.81 | learning rate: 1.343E-04 | global batch size: 256 | lm loss: 2.214498E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.873 | TFLOPs: 19.17 | +31: iteration 16630/ 39672 | consumed samples: 4257280 | consumed tokens: 8718909440 | elapsed time per iteration (s): 0.78 | learning rate: 1.342E-04 | global batch size: 256 | lm loss: 2.217666E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.116 | TFLOPs: 19.73 | +31: iteration 16640/ 39672 | consumed samples: 4259840 | consumed tokens: 8724152320 | elapsed time per iteration (s): 0.80 | learning rate: 1.341E-04 | global batch size: 256 | lm loss: 2.208949E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.168 | TFLOPs: 19.31 | +31: iteration 16650/ 39672 | consumed samples: 4262400 | consumed tokens: 8729395200 | elapsed time per iteration (s): 0.80 | learning rate: 1.341E-04 | global batch size: 256 | lm loss: 2.197959E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.776 | TFLOPs: 19.29 | +31: iteration 16660/ 39672 | consumed samples: 4264960 | consumed tokens: 8734638080 | elapsed time per iteration (s): 0.77 | learning rate: 1.340E-04 | global batch size: 256 | lm loss: 2.208836E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.808 | TFLOPs: 20.13 | +31: iteration 16670/ 39672 | consumed samples: 4267520 | consumed tokens: 8739880960 | elapsed time per iteration (s): 0.74 | learning rate: 1.339E-04 | global batch size: 256 | lm loss: 2.191280E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.635 | TFLOPs: 20.91 | +31: iteration 16680/ 39672 | consumed samples: 4270080 | consumed tokens: 8745123840 | elapsed time per iteration (s): 0.73 | learning rate: 1.339E-04 | global batch size: 256 | lm loss: 2.216258E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.612 | TFLOPs: 21.15 | +31: iteration 16690/ 39672 | consumed samples: 4272640 | consumed tokens: 8750366720 | elapsed time per iteration (s): 0.73 | learning rate: 1.338E-04 | global batch size: 256 | lm loss: 2.185201E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.409 | TFLOPs: 21.20 | +31: iteration 16700/ 39672 | consumed samples: 4275200 | consumed tokens: 8755609600 | elapsed time per iteration (s): 0.78 | learning rate: 1.337E-04 | global batch size: 256 | lm loss: 2.220461E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.808 | TFLOPs: 19.89 | +31: iteration 16710/ 39672 | consumed samples: 4277760 | consumed tokens: 8760852480 | elapsed time per iteration (s): 0.77 | learning rate: 1.337E-04 | global batch size: 256 | lm loss: 2.214241E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.159 | TFLOPs: 20.22 | +31: iteration 16720/ 39672 | consumed samples: 4280320 | consumed tokens: 8766095360 | elapsed time per iteration (s): 0.80 | learning rate: 1.336E-04 | global batch size: 256 | lm loss: 2.162152E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.092 | TFLOPs: 19.36 | +31: iteration 16730/ 39672 | consumed samples: 4282880 | consumed tokens: 8771338240 | elapsed time per iteration (s): 0.77 | learning rate: 1.335E-04 | global batch size: 256 | lm loss: 2.239707E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.484 | TFLOPs: 20.17 | +31: iteration 16740/ 39672 | consumed samples: 4285440 | consumed tokens: 8776581120 | elapsed time per iteration (s): 0.79 | learning rate: 1.334E-04 | global batch size: 256 | lm loss: 2.212403E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.339 | TFLOPs: 19.56 | +31: iteration 16750/ 39672 | consumed samples: 4288000 | consumed tokens: 8781824000 | elapsed time per iteration (s): 0.79 | learning rate: 1.334E-04 | global batch size: 256 | lm loss: 2.216719E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.349 | TFLOPs: 19.62 | +31: iteration 16760/ 39672 | consumed samples: 4290560 | consumed tokens: 8787066880 | elapsed time per iteration (s): 0.80 | learning rate: 1.333E-04 | global batch size: 256 | lm loss: 2.213798E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.030 | TFLOPs: 19.24 | +31: iteration 16770/ 39672 | consumed samples: 4293120 | consumed tokens: 8792309760 | elapsed time per iteration (s): 0.82 | learning rate: 1.332E-04 | global batch size: 256 | lm loss: 2.187017E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.114 | TFLOPs: 18.82 | +31: iteration 16780/ 39672 | consumed samples: 4295680 | consumed tokens: 8797552640 | elapsed time per iteration (s): 0.84 | learning rate: 1.332E-04 | global batch size: 256 | lm loss: 2.210575E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.282 | TFLOPs: 18.53 | +31: iteration 16790/ 39672 | consumed samples: 4298240 | consumed tokens: 8802795520 | elapsed time per iteration (s): 0.83 | learning rate: 1.331E-04 | global batch size: 256 | lm loss: 2.183212E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.412 | TFLOPs: 18.72 | +31: iteration 16800/ 39672 | consumed samples: 4300800 | consumed tokens: 8808038400 | elapsed time per iteration (s): 0.83 | learning rate: 1.330E-04 | global batch size: 256 | lm loss: 2.208953E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.423 | TFLOPs: 18.60 | +31: iteration 16810/ 39672 | consumed samples: 4303360 | consumed tokens: 8813281280 | elapsed time per iteration (s): 0.81 | learning rate: 1.330E-04 | global batch size: 256 | lm loss: 2.185273E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.201 | TFLOPs: 19.13 | +31: iteration 16820/ 39672 | consumed samples: 4305920 | consumed tokens: 8818524160 | elapsed time per iteration (s): 0.80 | learning rate: 1.329E-04 | global batch size: 256 | lm loss: 2.183790E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.372 | TFLOPs: 19.38 | +31: iteration 16830/ 39672 | consumed samples: 4308480 | consumed tokens: 8823767040 | elapsed time per iteration (s): 0.84 | learning rate: 1.328E-04 | global batch size: 256 | lm loss: 2.204345E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.796 | TFLOPs: 18.44 | +31: iteration 16840/ 39672 | consumed samples: 4311040 | consumed tokens: 8829009920 | elapsed time per iteration (s): 0.78 | learning rate: 1.327E-04 | global batch size: 256 | lm loss: 2.184401E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.884 | TFLOPs: 19.84 | +31: iteration 16850/ 39672 | consumed samples: 4313600 | consumed tokens: 8834252800 | elapsed time per iteration (s): 0.82 | learning rate: 1.327E-04 | global batch size: 256 | lm loss: 2.202817E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.255 | TFLOPs: 18.95 | +31: iteration 16860/ 39672 | consumed samples: 4316160 | consumed tokens: 8839495680 | elapsed time per iteration (s): 0.72 | learning rate: 1.326E-04 | global batch size: 256 | lm loss: 2.215234E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.230 | TFLOPs: 21.61 | +31: iteration 16870/ 39672 | consumed samples: 4318720 | consumed tokens: 8844738560 | elapsed time per iteration (s): 0.76 | learning rate: 1.325E-04 | global batch size: 256 | lm loss: 2.220418E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.719 | TFLOPs: 20.43 | +31: iteration 16880/ 39672 | consumed samples: 4321280 | consumed tokens: 8849981440 | elapsed time per iteration (s): 0.73 | learning rate: 1.325E-04 | global batch size: 256 | lm loss: 2.183498E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.384 | TFLOPs: 21.26 | +31: iteration 16890/ 39672 | consumed samples: 4323840 | consumed tokens: 8855224320 | elapsed time per iteration (s): 0.81 | learning rate: 1.324E-04 | global batch size: 256 | lm loss: 2.217587E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.404 | TFLOPs: 19.20 | +31: iteration 16900/ 39672 | consumed samples: 4326400 | consumed tokens: 8860467200 | elapsed time per iteration (s): 0.84 | learning rate: 1.323E-04 | global batch size: 256 | lm loss: 2.192463E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.385 | TFLOPs: 18.54 | +31: iteration 16910/ 39672 | consumed samples: 4328960 | consumed tokens: 8865710080 | elapsed time per iteration (s): 0.75 | learning rate: 1.323E-04 | global batch size: 256 | lm loss: 2.185033E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.435 | TFLOPs: 20.66 | +31: iteration 16920/ 39672 | consumed samples: 4331520 | consumed tokens: 8870952960 | elapsed time per iteration (s): 0.77 | learning rate: 1.322E-04 | global batch size: 256 | lm loss: 2.182583E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.948 | TFLOPs: 20.08 | +31: iteration 16930/ 39672 | consumed samples: 4334080 | consumed tokens: 8876195840 | elapsed time per iteration (s): 0.80 | learning rate: 1.321E-04 | global batch size: 256 | lm loss: 2.187354E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.898 | TFLOPs: 19.35 | +31: iteration 16940/ 39672 | consumed samples: 4336640 | consumed tokens: 8881438720 | elapsed time per iteration (s): 0.82 | learning rate: 1.321E-04 | global batch size: 256 | lm loss: 2.203030E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.299 | TFLOPs: 18.83 | +31: iteration 16950/ 39672 | consumed samples: 4339200 | consumed tokens: 8886681600 | elapsed time per iteration (s): 0.81 | learning rate: 1.320E-04 | global batch size: 256 | lm loss: 2.183115E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.778 | TFLOPs: 19.22 | +31: iteration 16960/ 39672 | consumed samples: 4341760 | consumed tokens: 8891924480 | elapsed time per iteration (s): 0.84 | learning rate: 1.319E-04 | global batch size: 256 | lm loss: 2.200405E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.155 | TFLOPs: 18.46 | +31: iteration 16970/ 39672 | consumed samples: 4344320 | consumed tokens: 8897167360 | elapsed time per iteration (s): 0.81 | learning rate: 1.318E-04 | global batch size: 256 | lm loss: 2.199411E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.500 | TFLOPs: 19.21 | +31: iteration 16980/ 39672 | consumed samples: 4346880 | consumed tokens: 8902410240 | elapsed time per iteration (s): 0.81 | learning rate: 1.318E-04 | global batch size: 256 | lm loss: 2.228430E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.295 | TFLOPs: 19.07 | +31: iteration 16990/ 39672 | consumed samples: 4349440 | consumed tokens: 8907653120 | elapsed time per iteration (s): 0.82 | learning rate: 1.317E-04 | global batch size: 256 | lm loss: 2.219424E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.360 | TFLOPs: 18.96 | +31: iteration 17000/ 39672 | consumed samples: 4352000 | consumed tokens: 8912896000 | elapsed time per iteration (s): 0.81 | learning rate: 1.316E-04 | global batch size: 256 | lm loss: 2.215192E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.172 | TFLOPs: 19.13 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 17000 | lm loss value: 2.197433E+00 | lm loss PPL: 9.001880E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 17010/ 39672 | consumed samples: 4354560 | consumed tokens: 8918138880 | elapsed time per iteration (s): 0.83 | learning rate: 1.316E-04 | global batch size: 256 | lm loss: 2.211808E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.627 | TFLOPs: 18.55 | +31: iteration 17020/ 39672 | consumed samples: 4357120 | consumed tokens: 8923381760 | elapsed time per iteration (s): 0.77 | learning rate: 1.315E-04 | global batch size: 256 | lm loss: 2.221696E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.747 | TFLOPs: 20.13 | +31: iteration 17030/ 39672 | consumed samples: 4359680 | consumed tokens: 8928624640 | elapsed time per iteration (s): 0.76 | learning rate: 1.314E-04 | global batch size: 256 | lm loss: 2.219386E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.443 | TFLOPs: 20.47 | +31: iteration 17040/ 39672 | consumed samples: 4362240 | consumed tokens: 8933867520 | elapsed time per iteration (s): 0.79 | learning rate: 1.314E-04 | global batch size: 256 | lm loss: 2.218303E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.062 | TFLOPs: 19.48 | +31: iteration 17050/ 39672 | consumed samples: 4364800 | consumed tokens: 8939110400 | elapsed time per iteration (s): 0.77 | learning rate: 1.313E-04 | global batch size: 256 | lm loss: 2.225426E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.625 | TFLOPs: 20.06 | +31: iteration 17060/ 39672 | consumed samples: 4367360 | consumed tokens: 8944353280 | elapsed time per iteration (s): 0.75 | learning rate: 1.312E-04 | global batch size: 256 | lm loss: 2.153374E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.665 | TFLOPs: 20.67 | +31: iteration 17070/ 39672 | consumed samples: 4369920 | consumed tokens: 8949596160 | elapsed time per iteration (s): 0.77 | learning rate: 1.311E-04 | global batch size: 256 | lm loss: 2.206656E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.104 | TFLOPs: 20.15 | +31: iteration 17080/ 39672 | consumed samples: 4372480 | consumed tokens: 8954839040 | elapsed time per iteration (s): 0.78 | learning rate: 1.311E-04 | global batch size: 256 | lm loss: 2.209611E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.515 | TFLOPs: 19.75 | +31: iteration 17090/ 39672 | consumed samples: 4375040 | consumed tokens: 8960081920 | elapsed time per iteration (s): 0.77 | learning rate: 1.310E-04 | global batch size: 256 | lm loss: 2.206303E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.606 | TFLOPs: 20.24 | +31: iteration 17100/ 39672 | consumed samples: 4377600 | consumed tokens: 8965324800 | elapsed time per iteration (s): 0.81 | learning rate: 1.309E-04 | global batch size: 256 | lm loss: 2.203242E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.619 | TFLOPs: 19.09 | +31: iteration 17110/ 39672 | consumed samples: 4380160 | consumed tokens: 8970567680 | elapsed time per iteration (s): 0.82 | learning rate: 1.309E-04 | global batch size: 256 | lm loss: 2.192171E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.883 | TFLOPs: 18.81 | +31: iteration 17120/ 39672 | consumed samples: 4382720 | consumed tokens: 8975810560 | elapsed time per iteration (s): 0.77 | learning rate: 1.308E-04 | global batch size: 256 | lm loss: 2.236415E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.086 | TFLOPs: 20.09 | +31: iteration 17130/ 39672 | consumed samples: 4385280 | consumed tokens: 8981053440 | elapsed time per iteration (s): 0.79 | learning rate: 1.307E-04 | global batch size: 256 | lm loss: 2.185938E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.059 | TFLOPs: 19.54 | +31: iteration 17140/ 39672 | consumed samples: 4387840 | consumed tokens: 8986296320 | elapsed time per iteration (s): 0.79 | learning rate: 1.307E-04 | global batch size: 256 | lm loss: 2.198817E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.621 | TFLOPs: 19.58 | +31: iteration 17150/ 39672 | consumed samples: 4390400 | consumed tokens: 8991539200 | elapsed time per iteration (s): 0.77 | learning rate: 1.306E-04 | global batch size: 256 | lm loss: 2.201820E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.386 | TFLOPs: 20.17 | +31: iteration 17160/ 39672 | consumed samples: 4392960 | consumed tokens: 8996782080 | elapsed time per iteration (s): 0.75 | learning rate: 1.305E-04 | global batch size: 256 | lm loss: 2.194973E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.114 | TFLOPs: 20.58 | +31: iteration 17170/ 39672 | consumed samples: 4395520 | consumed tokens: 9002024960 | elapsed time per iteration (s): 0.76 | learning rate: 1.304E-04 | global batch size: 256 | lm loss: 2.217850E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.973 | TFLOPs: 20.26 | +31: iteration 17180/ 39672 | consumed samples: 4398080 | consumed tokens: 9007267840 | elapsed time per iteration (s): 0.76 | learning rate: 1.304E-04 | global batch size: 256 | lm loss: 2.193895E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.921 | TFLOPs: 20.50 | +31: iteration 17190/ 39672 | consumed samples: 4400640 | consumed tokens: 9012510720 | elapsed time per iteration (s): 0.76 | learning rate: 1.303E-04 | global batch size: 256 | lm loss: 2.220260E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.536 | TFLOPs: 20.48 | +31: iteration 17200/ 39672 | consumed samples: 4403200 | consumed tokens: 9017753600 | elapsed time per iteration (s): 0.78 | learning rate: 1.302E-04 | global batch size: 256 | lm loss: 2.163948E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.756 | TFLOPs: 19.95 | +31: iteration 17210/ 39672 | consumed samples: 4405760 | consumed tokens: 9022996480 | elapsed time per iteration (s): 0.73 | learning rate: 1.302E-04 | global batch size: 256 | lm loss: 2.182632E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.287 | TFLOPs: 21.25 | +31: iteration 17220/ 39672 | consumed samples: 4408320 | consumed tokens: 9028239360 | elapsed time per iteration (s): 0.76 | learning rate: 1.301E-04 | global batch size: 256 | lm loss: 2.181073E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.326 | TFLOPs: 20.47 | +31: iteration 17230/ 39672 | consumed samples: 4410880 | consumed tokens: 9033482240 | elapsed time per iteration (s): 0.79 | learning rate: 1.300E-04 | global batch size: 256 | lm loss: 2.222760E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.279 | TFLOPs: 19.62 | +31: iteration 17240/ 39672 | consumed samples: 4413440 | consumed tokens: 9038725120 | elapsed time per iteration (s): 0.78 | learning rate: 1.300E-04 | global batch size: 256 | lm loss: 2.222525E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.227 | TFLOPs: 19.74 | +31: iteration 17250/ 39672 | consumed samples: 4416000 | consumed tokens: 9043968000 | elapsed time per iteration (s): 0.80 | learning rate: 1.299E-04 | global batch size: 256 | lm loss: 2.190822E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.860 | TFLOPs: 19.41 | +31: iteration 17260/ 39672 | consumed samples: 4418560 | consumed tokens: 9049210880 | elapsed time per iteration (s): 0.73 | learning rate: 1.298E-04 | global batch size: 256 | lm loss: 2.201053E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.855 | TFLOPs: 21.10 | +31: iteration 17270/ 39672 | consumed samples: 4421120 | consumed tokens: 9054453760 | elapsed time per iteration (s): 0.77 | learning rate: 1.297E-04 | global batch size: 256 | lm loss: 2.221220E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.941 | TFLOPs: 20.14 | +31: iteration 17280/ 39672 | consumed samples: 4423680 | consumed tokens: 9059696640 | elapsed time per iteration (s): 0.76 | learning rate: 1.297E-04 | global batch size: 256 | lm loss: 2.202836E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.272 | TFLOPs: 20.46 | +31: iteration 17290/ 39672 | consumed samples: 4426240 | consumed tokens: 9064939520 | elapsed time per iteration (s): 0.77 | learning rate: 1.296E-04 | global batch size: 256 | lm loss: 2.208323E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.329 | TFLOPs: 19.98 | +31: iteration 17300/ 39672 | consumed samples: 4428800 | consumed tokens: 9070182400 | elapsed time per iteration (s): 0.80 | learning rate: 1.295E-04 | global batch size: 256 | lm loss: 2.211024E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.535 | TFLOPs: 19.33 | +31: iteration 17310/ 39672 | consumed samples: 4431360 | consumed tokens: 9075425280 | elapsed time per iteration (s): 0.74 | learning rate: 1.295E-04 | global batch size: 256 | lm loss: 2.181581E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.151 | TFLOPs: 20.82 | +31: iteration 17320/ 39672 | consumed samples: 4433920 | consumed tokens: 9080668160 | elapsed time per iteration (s): 0.75 | learning rate: 1.294E-04 | global batch size: 256 | lm loss: 2.190433E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.812 | TFLOPs: 20.68 | +31: iteration 17330/ 39672 | consumed samples: 4436480 | consumed tokens: 9085911040 | elapsed time per iteration (s): 0.75 | learning rate: 1.293E-04 | global batch size: 256 | lm loss: 2.212540E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.721 | TFLOPs: 20.67 | +31: iteration 17340/ 39672 | consumed samples: 4439040 | consumed tokens: 9091153920 | elapsed time per iteration (s): 0.77 | learning rate: 1.292E-04 | global batch size: 256 | lm loss: 2.188344E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.632 | TFLOPs: 20.24 | +31: iteration 17350/ 39672 | consumed samples: 4441600 | consumed tokens: 9096396800 | elapsed time per iteration (s): 0.72 | learning rate: 1.292E-04 | global batch size: 256 | lm loss: 2.180902E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.819 | TFLOPs: 21.47 | +31: iteration 17360/ 39672 | consumed samples: 4444160 | consumed tokens: 9101639680 | elapsed time per iteration (s): 0.76 | learning rate: 1.291E-04 | global batch size: 256 | lm loss: 2.173525E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.018 | TFLOPs: 20.45 | +31: iteration 17370/ 39672 | consumed samples: 4446720 | consumed tokens: 9106882560 | elapsed time per iteration (s): 0.74 | learning rate: 1.290E-04 | global batch size: 256 | lm loss: 2.178307E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.342 | TFLOPs: 21.01 | +31: iteration 17380/ 39672 | consumed samples: 4449280 | consumed tokens: 9112125440 | elapsed time per iteration (s): 0.84 | learning rate: 1.290E-04 | global batch size: 256 | lm loss: 2.209162E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.871 | TFLOPs: 18.38 | +31: iteration 17390/ 39672 | consumed samples: 4451840 | consumed tokens: 9117368320 | elapsed time per iteration (s): 0.85 | learning rate: 1.289E-04 | global batch size: 256 | lm loss: 2.227659E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.985 | TFLOPs: 18.27 | +31: iteration 17400/ 39672 | consumed samples: 4454400 | consumed tokens: 9122611200 | elapsed time per iteration (s): 0.80 | learning rate: 1.288E-04 | global batch size: 256 | lm loss: 2.205530E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.316 | TFLOPs: 19.32 | +31: iteration 17410/ 39672 | consumed samples: 4456960 | consumed tokens: 9127854080 | elapsed time per iteration (s): 0.83 | learning rate: 1.288E-04 | global batch size: 256 | lm loss: 2.195260E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.069 | TFLOPs: 18.58 | +31: iteration 17420/ 39672 | consumed samples: 4459520 | consumed tokens: 9133096960 | elapsed time per iteration (s): 0.81 | learning rate: 1.287E-04 | global batch size: 256 | lm loss: 2.196735E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.602 | TFLOPs: 19.03 | +31: iteration 17430/ 39672 | consumed samples: 4462080 | consumed tokens: 9138339840 | elapsed time per iteration (s): 0.78 | learning rate: 1.286E-04 | global batch size: 256 | lm loss: 2.215306E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.894 | TFLOPs: 19.78 | +31: iteration 17440/ 39672 | consumed samples: 4464640 | consumed tokens: 9143582720 | elapsed time per iteration (s): 0.80 | learning rate: 1.285E-04 | global batch size: 256 | lm loss: 2.182797E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.231 | TFLOPs: 19.43 | +31: iteration 17450/ 39672 | consumed samples: 4467200 | consumed tokens: 9148825600 | elapsed time per iteration (s): 0.82 | learning rate: 1.285E-04 | global batch size: 256 | lm loss: 2.209596E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.190 | TFLOPs: 18.89 | +31: iteration 17460/ 39672 | consumed samples: 4469760 | consumed tokens: 9154068480 | elapsed time per iteration (s): 0.83 | learning rate: 1.284E-04 | global batch size: 256 | lm loss: 2.215216E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.309 | TFLOPs: 18.65 | +31: iteration 17470/ 39672 | consumed samples: 4472320 | consumed tokens: 9159311360 | elapsed time per iteration (s): 0.83 | learning rate: 1.283E-04 | global batch size: 256 | lm loss: 2.167804E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.368 | TFLOPs: 18.59 | +31: iteration 17480/ 39672 | consumed samples: 4474880 | consumed tokens: 9164554240 | elapsed time per iteration (s): 0.80 | learning rate: 1.283E-04 | global batch size: 256 | lm loss: 2.200427E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.460 | TFLOPs: 19.45 | +31: iteration 17490/ 39672 | consumed samples: 4477440 | consumed tokens: 9169797120 | elapsed time per iteration (s): 0.75 | learning rate: 1.282E-04 | global batch size: 256 | lm loss: 2.221688E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.001 | TFLOPs: 20.75 | +31: iteration 17500/ 39672 | consumed samples: 4480000 | consumed tokens: 9175040000 | elapsed time per iteration (s): 0.77 | learning rate: 1.281E-04 | global batch size: 256 | lm loss: 2.176117E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.359 | TFLOPs: 20.05 | +31: iteration 17510/ 39672 | consumed samples: 4482560 | consumed tokens: 9180282880 | elapsed time per iteration (s): 0.84 | learning rate: 1.281E-04 | global batch size: 256 | lm loss: 2.179590E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.699 | TFLOPs: 18.37 | +31: iteration 17520/ 39672 | consumed samples: 4485120 | consumed tokens: 9185525760 | elapsed time per iteration (s): 0.85 | learning rate: 1.280E-04 | global batch size: 256 | lm loss: 2.200215E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.643 | TFLOPs: 18.31 | +31: iteration 17530/ 39672 | consumed samples: 4487680 | consumed tokens: 9190768640 | elapsed time per iteration (s): 0.81 | learning rate: 1.279E-04 | global batch size: 256 | lm loss: 2.229255E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.704 | TFLOPs: 19.04 | +31: iteration 17540/ 39672 | consumed samples: 4490240 | consumed tokens: 9196011520 | elapsed time per iteration (s): 0.76 | learning rate: 1.278E-04 | global batch size: 256 | lm loss: 2.231281E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.931 | TFLOPs: 20.44 | +31: iteration 17550/ 39672 | consumed samples: 4492800 | consumed tokens: 9201254400 | elapsed time per iteration (s): 0.76 | learning rate: 1.278E-04 | global batch size: 256 | lm loss: 2.207245E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.083 | TFLOPs: 20.39 | +31: iteration 17560/ 39672 | consumed samples: 4495360 | consumed tokens: 9206497280 | elapsed time per iteration (s): 0.83 | learning rate: 1.277E-04 | global batch size: 256 | lm loss: 2.184687E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.578 | TFLOPs: 18.73 | +31: iteration 17570/ 39672 | consumed samples: 4497920 | consumed tokens: 9211740160 | elapsed time per iteration (s): 0.79 | learning rate: 1.276E-04 | global batch size: 256 | lm loss: 2.184524E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.832 | TFLOPs: 19.53 | +31: iteration 17580/ 39672 | consumed samples: 4500480 | consumed tokens: 9216983040 | elapsed time per iteration (s): 0.83 | learning rate: 1.276E-04 | global batch size: 256 | lm loss: 2.211121E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.792 | TFLOPs: 18.62 | +31: iteration 17590/ 39672 | consumed samples: 4503040 | consumed tokens: 9222225920 | elapsed time per iteration (s): 0.75 | learning rate: 1.275E-04 | global batch size: 256 | lm loss: 2.181528E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.596 | TFLOPs: 20.73 | +31: iteration 17600/ 39672 | consumed samples: 4505600 | consumed tokens: 9227468800 | elapsed time per iteration (s): 0.79 | learning rate: 1.274E-04 | global batch size: 256 | lm loss: 2.217116E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.525 | TFLOPs: 19.69 | +31: iteration 17610/ 39672 | consumed samples: 4508160 | consumed tokens: 9232711680 | elapsed time per iteration (s): 0.79 | learning rate: 1.273E-04 | global batch size: 256 | lm loss: 2.202018E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.180 | TFLOPs: 19.49 | +31: iteration 17620/ 39672 | consumed samples: 4510720 | consumed tokens: 9237954560 | elapsed time per iteration (s): 0.76 | learning rate: 1.273E-04 | global batch size: 256 | lm loss: 2.211654E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.752 | TFLOPs: 20.37 | +31: iteration 17630/ 39672 | consumed samples: 4513280 | consumed tokens: 9243197440 | elapsed time per iteration (s): 0.74 | learning rate: 1.272E-04 | global batch size: 256 | lm loss: 2.182388E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.973 | TFLOPs: 20.93 | +31: iteration 17640/ 39672 | consumed samples: 4515840 | consumed tokens: 9248440320 | elapsed time per iteration (s): 0.77 | learning rate: 1.271E-04 | global batch size: 256 | lm loss: 2.182384E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.116 | TFLOPs: 20.09 | +31: iteration 17650/ 39672 | consumed samples: 4518400 | consumed tokens: 9253683200 | elapsed time per iteration (s): 0.76 | learning rate: 1.271E-04 | global batch size: 256 | lm loss: 2.206224E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.721 | TFLOPs: 20.31 | +31: iteration 17660/ 39672 | consumed samples: 4520960 | consumed tokens: 9258926080 | elapsed time per iteration (s): 0.82 | learning rate: 1.270E-04 | global batch size: 256 | lm loss: 2.210148E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.625 | TFLOPs: 18.79 | +31: iteration 17670/ 39672 | consumed samples: 4523520 | consumed tokens: 9264168960 | elapsed time per iteration (s): 0.80 | learning rate: 1.269E-04 | global batch size: 256 | lm loss: 2.158652E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.206 | TFLOPs: 19.31 | +31: iteration 17680/ 39672 | consumed samples: 4526080 | consumed tokens: 9269411840 | elapsed time per iteration (s): 0.87 | learning rate: 1.269E-04 | global batch size: 256 | lm loss: 2.195109E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.278 | TFLOPs: 17.86 | +31: iteration 17690/ 39672 | consumed samples: 4528640 | consumed tokens: 9274654720 | elapsed time per iteration (s): 0.81 | learning rate: 1.268E-04 | global batch size: 256 | lm loss: 2.225495E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.646 | TFLOPs: 19.04 | +31: iteration 17700/ 39672 | consumed samples: 4531200 | consumed tokens: 9279897600 | elapsed time per iteration (s): 0.81 | learning rate: 1.267E-04 | global batch size: 256 | lm loss: 2.202411E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.084 | TFLOPs: 19.12 | +31: iteration 17710/ 39672 | consumed samples: 4533760 | consumed tokens: 9285140480 | elapsed time per iteration (s): 0.82 | learning rate: 1.266E-04 | global batch size: 256 | lm loss: 2.193842E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.449 | TFLOPs: 18.78 | +31: iteration 17720/ 39672 | consumed samples: 4536320 | consumed tokens: 9290383360 | elapsed time per iteration (s): 0.85 | learning rate: 1.266E-04 | global batch size: 256 | lm loss: 2.199644E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.416 | TFLOPs: 18.30 | +31: iteration 17730/ 39672 | consumed samples: 4538880 | consumed tokens: 9295626240 | elapsed time per iteration (s): 0.80 | learning rate: 1.265E-04 | global batch size: 256 | lm loss: 2.158008E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.923 | TFLOPs: 19.29 | +31: iteration 17740/ 39672 | consumed samples: 4541440 | consumed tokens: 9300869120 | elapsed time per iteration (s): 0.80 | learning rate: 1.264E-04 | global batch size: 256 | lm loss: 2.194069E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.089 | TFLOPs: 19.24 | +31: iteration 17750/ 39672 | consumed samples: 4544000 | consumed tokens: 9306112000 | elapsed time per iteration (s): 0.82 | learning rate: 1.264E-04 | global batch size: 256 | lm loss: 2.218161E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.360 | TFLOPs: 18.84 | +31: iteration 17760/ 39672 | consumed samples: 4546560 | consumed tokens: 9311354880 | elapsed time per iteration (s): 0.86 | learning rate: 1.263E-04 | global batch size: 256 | lm loss: 2.219058E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.745 | TFLOPs: 18.01 | +31: iteration 17770/ 39672 | consumed samples: 4549120 | consumed tokens: 9316597760 | elapsed time per iteration (s): 0.85 | learning rate: 1.262E-04 | global batch size: 256 | lm loss: 2.211618E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.111 | TFLOPs: 18.28 | +31: iteration 17780/ 39672 | consumed samples: 4551680 | consumed tokens: 9321840640 | elapsed time per iteration (s): 0.82 | learning rate: 1.261E-04 | global batch size: 256 | lm loss: 2.211313E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.017 | TFLOPs: 19.00 | +31: iteration 17790/ 39672 | consumed samples: 4554240 | consumed tokens: 9327083520 | elapsed time per iteration (s): 0.79 | learning rate: 1.261E-04 | global batch size: 256 | lm loss: 2.173989E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.084 | TFLOPs: 19.61 | +31: iteration 17800/ 39672 | consumed samples: 4556800 | consumed tokens: 9332326400 | elapsed time per iteration (s): 0.81 | learning rate: 1.260E-04 | global batch size: 256 | lm loss: 2.207779E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.455 | TFLOPs: 19.08 | +31: iteration 17810/ 39672 | consumed samples: 4559360 | consumed tokens: 9337569280 | elapsed time per iteration (s): 0.83 | learning rate: 1.259E-04 | global batch size: 256 | lm loss: 2.203099E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.251 | TFLOPs: 18.59 | +31: iteration 17820/ 39672 | consumed samples: 4561920 | consumed tokens: 9342812160 | elapsed time per iteration (s): 0.83 | learning rate: 1.259E-04 | global batch size: 256 | lm loss: 2.209629E+00 | grad norm: 1.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.325 | TFLOPs: 18.65 | +31: iteration 17830/ 39672 | consumed samples: 4564480 | consumed tokens: 9348055040 | elapsed time per iteration (s): 0.79 | learning rate: 1.258E-04 | global batch size: 256 | lm loss: 2.230655E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.046 | TFLOPs: 19.48 | +31: iteration 17840/ 39672 | consumed samples: 4567040 | consumed tokens: 9353297920 | elapsed time per iteration (s): 0.81 | learning rate: 1.257E-04 | global batch size: 256 | lm loss: 2.203927E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.652 | TFLOPs: 19.16 | +31: iteration 17850/ 39672 | consumed samples: 4569600 | consumed tokens: 9358540800 | elapsed time per iteration (s): 0.82 | learning rate: 1.256E-04 | global batch size: 256 | lm loss: 2.199846E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.034 | TFLOPs: 19.00 | +31: iteration 17860/ 39672 | consumed samples: 4572160 | consumed tokens: 9363783680 | elapsed time per iteration (s): 0.78 | learning rate: 1.256E-04 | global batch size: 256 | lm loss: 2.185773E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.407 | TFLOPs: 19.93 | +31: iteration 17870/ 39672 | consumed samples: 4574720 | consumed tokens: 9369026560 | elapsed time per iteration (s): 0.85 | learning rate: 1.255E-04 | global batch size: 256 | lm loss: 2.208540E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.580 | TFLOPs: 18.24 | +31: iteration 17880/ 39672 | consumed samples: 4577280 | consumed tokens: 9374269440 | elapsed time per iteration (s): 0.90 | learning rate: 1.254E-04 | global batch size: 256 | lm loss: 2.207013E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 285.304 | TFLOPs: 17.26 | +31: iteration 17890/ 39672 | consumed samples: 4579840 | consumed tokens: 9379512320 | elapsed time per iteration (s): 0.81 | learning rate: 1.254E-04 | global batch size: 256 | lm loss: 2.178886E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.471 | TFLOPs: 19.15 | +31: iteration 17900/ 39672 | consumed samples: 4582400 | consumed tokens: 9384755200 | elapsed time per iteration (s): 0.83 | learning rate: 1.253E-04 | global batch size: 256 | lm loss: 2.236464E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.988 | TFLOPs: 18.69 | +31: iteration 17910/ 39672 | consumed samples: 4584960 | consumed tokens: 9389998080 | elapsed time per iteration (s): 0.84 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 2.149860E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.342 | TFLOPs: 18.47 | +31: iteration 17920/ 39672 | consumed samples: 4587520 | consumed tokens: 9395240960 | elapsed time per iteration (s): 0.80 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 2.192455E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.220 | TFLOPs: 19.43 | +31: iteration 17930/ 39672 | consumed samples: 4590080 | consumed tokens: 9400483840 | elapsed time per iteration (s): 0.83 | learning rate: 1.251E-04 | global batch size: 256 | lm loss: 2.211605E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.629 | TFLOPs: 18.73 | +31: iteration 17940/ 39672 | consumed samples: 4592640 | consumed tokens: 9405726720 | elapsed time per iteration (s): 0.81 | learning rate: 1.250E-04 | global batch size: 256 | lm loss: 2.197205E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.011 | TFLOPs: 19.12 | +31: iteration 17950/ 39672 | consumed samples: 4595200 | consumed tokens: 9410969600 | elapsed time per iteration (s): 0.81 | learning rate: 1.249E-04 | global batch size: 256 | lm loss: 2.206320E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.353 | TFLOPs: 19.20 | +31: iteration 17960/ 39672 | consumed samples: 4597760 | consumed tokens: 9416212480 | elapsed time per iteration (s): 0.79 | learning rate: 1.249E-04 | global batch size: 256 | lm loss: 2.181747E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.620 | TFLOPs: 19.52 | +31: iteration 17970/ 39672 | consumed samples: 4600320 | consumed tokens: 9421455360 | elapsed time per iteration (s): 0.83 | learning rate: 1.248E-04 | global batch size: 256 | lm loss: 2.190649E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.600 | TFLOPs: 18.73 | +31: iteration 17980/ 39672 | consumed samples: 4602880 | consumed tokens: 9426698240 | elapsed time per iteration (s): 0.80 | learning rate: 1.247E-04 | global batch size: 256 | lm loss: 2.209846E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.657 | TFLOPs: 19.28 | +31: iteration 17990/ 39672 | consumed samples: 4605440 | consumed tokens: 9431941120 | elapsed time per iteration (s): 0.79 | learning rate: 1.247E-04 | global batch size: 256 | lm loss: 2.195465E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.942 | TFLOPs: 19.60 | + 0: [2022-11-30 13:12:01,302] [INFO] [logging.py:68:log_dist] [Rank 0] step=18000, skipped=0, lr=[0.00012458359167705105, 0.00012458359167705105, 0.00012458359167705105], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 18000/ 39672 | consumed samples: 4608000 | consumed tokens: 9437184000 | elapsed time per iteration (s): 0.83 | learning rate: 1.246E-04 | global batch size: 256 | lm loss: 2.197554E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.785 | TFLOPs: 18.74 | + 0: steps: 18000 loss: 2.1620 iter time (s): 0.784 samples/sec: 326.437 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 18000 | lm loss value: 2.057942E+00 | lm loss PPL: 7.829837E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 18010/ 39672 | consumed samples: 4610560 | consumed tokens: 9442426880 | elapsed time per iteration (s): 0.85 | learning rate: 1.245E-04 | global batch size: 256 | lm loss: 2.216346E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.009 | TFLOPs: 18.15 | +31: iteration 18020/ 39672 | consumed samples: 4613120 | consumed tokens: 9447669760 | elapsed time per iteration (s): 0.80 | learning rate: 1.244E-04 | global batch size: 256 | lm loss: 2.214485E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.119 | TFLOPs: 19.37 | +31: iteration 18030/ 39672 | consumed samples: 4615680 | consumed tokens: 9452912640 | elapsed time per iteration (s): 0.80 | learning rate: 1.244E-04 | global batch size: 256 | lm loss: 2.184709E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.118 | TFLOPs: 19.31 | +31: iteration 18040/ 39672 | consumed samples: 4618240 | consumed tokens: 9458155520 | elapsed time per iteration (s): 0.76 | learning rate: 1.243E-04 | global batch size: 256 | lm loss: 2.205617E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.966 | TFLOPs: 20.51 | +31: iteration 18050/ 39672 | consumed samples: 4620800 | consumed tokens: 9463398400 | elapsed time per iteration (s): 0.71 | learning rate: 1.242E-04 | global batch size: 256 | lm loss: 2.201040E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 360.986 | TFLOPs: 21.84 | +31: iteration 18060/ 39672 | consumed samples: 4623360 | consumed tokens: 9468641280 | elapsed time per iteration (s): 0.76 | learning rate: 1.242E-04 | global batch size: 256 | lm loss: 2.176652E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.022 | TFLOPs: 20.39 | +31: iteration 18070/ 39672 | consumed samples: 4625920 | consumed tokens: 9473884160 | elapsed time per iteration (s): 0.75 | learning rate: 1.241E-04 | global batch size: 256 | lm loss: 2.207885E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.142 | TFLOPs: 20.70 | +31: iteration 18080/ 39672 | consumed samples: 4628480 | consumed tokens: 9479127040 | elapsed time per iteration (s): 0.76 | learning rate: 1.240E-04 | global batch size: 256 | lm loss: 2.182271E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.322 | TFLOPs: 20.35 | +31: iteration 18090/ 39672 | consumed samples: 4631040 | consumed tokens: 9484369920 | elapsed time per iteration (s): 0.77 | learning rate: 1.239E-04 | global batch size: 256 | lm loss: 2.207964E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.521 | TFLOPs: 20.12 | +31: iteration 18100/ 39672 | consumed samples: 4633600 | consumed tokens: 9489612800 | elapsed time per iteration (s): 0.74 | learning rate: 1.239E-04 | global batch size: 256 | lm loss: 2.191235E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.460 | TFLOPs: 20.84 | +31: iteration 18110/ 39672 | consumed samples: 4636160 | consumed tokens: 9494855680 | elapsed time per iteration (s): 0.79 | learning rate: 1.238E-04 | global batch size: 256 | lm loss: 2.224043E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.558 | TFLOPs: 19.70 | +31: iteration 18120/ 39672 | consumed samples: 4638720 | consumed tokens: 9500098560 | elapsed time per iteration (s): 0.78 | learning rate: 1.237E-04 | global batch size: 256 | lm loss: 2.222445E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.076 | TFLOPs: 19.79 | +31: iteration 18130/ 39672 | consumed samples: 4641280 | consumed tokens: 9505341440 | elapsed time per iteration (s): 0.76 | learning rate: 1.237E-04 | global batch size: 256 | lm loss: 2.208669E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.981 | TFLOPs: 20.45 | +31: iteration 18140/ 39672 | consumed samples: 4643840 | consumed tokens: 9510584320 | elapsed time per iteration (s): 0.73 | learning rate: 1.236E-04 | global batch size: 256 | lm loss: 2.179355E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.244 | TFLOPs: 21.13 | +31: iteration 18150/ 39672 | consumed samples: 4646400 | consumed tokens: 9515827200 | elapsed time per iteration (s): 0.80 | learning rate: 1.235E-04 | global batch size: 256 | lm loss: 2.169630E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.253 | TFLOPs: 19.43 | +31: iteration 18160/ 39672 | consumed samples: 4648960 | consumed tokens: 9521070080 | elapsed time per iteration (s): 0.79 | learning rate: 1.234E-04 | global batch size: 256 | lm loss: 2.199282E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.027 | TFLOPs: 19.60 | +31: iteration 18170/ 39672 | consumed samples: 4651520 | consumed tokens: 9526312960 | elapsed time per iteration (s): 0.79 | learning rate: 1.234E-04 | global batch size: 256 | lm loss: 2.232915E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.557 | TFLOPs: 19.70 | +31: iteration 18180/ 39672 | consumed samples: 4654080 | consumed tokens: 9531555840 | elapsed time per iteration (s): 0.74 | learning rate: 1.233E-04 | global batch size: 256 | lm loss: 2.211196E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.494 | TFLOPs: 21.02 | +31: iteration 18190/ 39672 | consumed samples: 4656640 | consumed tokens: 9536798720 | elapsed time per iteration (s): 0.77 | learning rate: 1.232E-04 | global batch size: 256 | lm loss: 2.195445E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.141 | TFLOPs: 20.09 | +31: iteration 18200/ 39672 | consumed samples: 4659200 | consumed tokens: 9542041600 | elapsed time per iteration (s): 0.77 | learning rate: 1.232E-04 | global batch size: 256 | lm loss: 2.219652E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.992 | TFLOPs: 20.21 | +31: iteration 18210/ 39672 | consumed samples: 4661760 | consumed tokens: 9547284480 | elapsed time per iteration (s): 0.75 | learning rate: 1.231E-04 | global batch size: 256 | lm loss: 2.166513E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.484 | TFLOPs: 20.54 | +31: iteration 18220/ 39672 | consumed samples: 4664320 | consumed tokens: 9552527360 | elapsed time per iteration (s): 0.72 | learning rate: 1.230E-04 | global batch size: 256 | lm loss: 2.223314E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.575 | TFLOPs: 21.57 | +31: iteration 18230/ 39672 | consumed samples: 4666880 | consumed tokens: 9557770240 | elapsed time per iteration (s): 0.78 | learning rate: 1.229E-04 | global batch size: 256 | lm loss: 2.181413E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.024 | TFLOPs: 19.84 | +31: iteration 18240/ 39672 | consumed samples: 4669440 | consumed tokens: 9563013120 | elapsed time per iteration (s): 0.74 | learning rate: 1.229E-04 | global batch size: 256 | lm loss: 2.173074E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.979 | TFLOPs: 20.93 | +31: iteration 18250/ 39672 | consumed samples: 4672000 | consumed tokens: 9568256000 | elapsed time per iteration (s): 0.74 | learning rate: 1.228E-04 | global batch size: 256 | lm loss: 2.193886E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.498 | TFLOPs: 20.96 | +31: iteration 18260/ 39672 | consumed samples: 4674560 | consumed tokens: 9573498880 | elapsed time per iteration (s): 0.74 | learning rate: 1.227E-04 | global batch size: 256 | lm loss: 2.161458E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.911 | TFLOPs: 21.05 | +31: iteration 18270/ 39672 | consumed samples: 4677120 | consumed tokens: 9578741760 | elapsed time per iteration (s): 0.78 | learning rate: 1.227E-04 | global batch size: 256 | lm loss: 2.179603E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.560 | TFLOPs: 19.94 | +31: iteration 18280/ 39672 | consumed samples: 4679680 | consumed tokens: 9583984640 | elapsed time per iteration (s): 0.73 | learning rate: 1.226E-04 | global batch size: 256 | lm loss: 2.207813E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.589 | TFLOPs: 21.15 | +31: iteration 18290/ 39672 | consumed samples: 4682240 | consumed tokens: 9589227520 | elapsed time per iteration (s): 0.77 | learning rate: 1.225E-04 | global batch size: 256 | lm loss: 2.190448E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.834 | TFLOPs: 20.01 | +31: iteration 18300/ 39672 | consumed samples: 4684800 | consumed tokens: 9594470400 | elapsed time per iteration (s): 0.77 | learning rate: 1.224E-04 | global batch size: 256 | lm loss: 2.211440E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.367 | TFLOPs: 20.11 | +31: iteration 18310/ 39672 | consumed samples: 4687360 | consumed tokens: 9599713280 | elapsed time per iteration (s): 0.77 | learning rate: 1.224E-04 | global batch size: 256 | lm loss: 2.221969E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.778 | TFLOPs: 20.19 | +31: iteration 18320/ 39672 | consumed samples: 4689920 | consumed tokens: 9604956160 | elapsed time per iteration (s): 0.79 | learning rate: 1.223E-04 | global batch size: 256 | lm loss: 2.172644E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.142 | TFLOPs: 19.49 | +31: iteration 18330/ 39672 | consumed samples: 4692480 | consumed tokens: 9610199040 | elapsed time per iteration (s): 0.77 | learning rate: 1.222E-04 | global batch size: 256 | lm loss: 2.192736E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.138 | TFLOPs: 20.09 | +31: iteration 18340/ 39672 | consumed samples: 4695040 | consumed tokens: 9615441920 | elapsed time per iteration (s): 0.77 | learning rate: 1.222E-04 | global batch size: 256 | lm loss: 2.197095E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.782 | TFLOPs: 20.01 | +31: iteration 18350/ 39672 | consumed samples: 4697600 | consumed tokens: 9620684800 | elapsed time per iteration (s): 0.80 | learning rate: 1.221E-04 | global batch size: 256 | lm loss: 2.199940E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.191 | TFLOPs: 19.37 | +31: iteration 18360/ 39672 | consumed samples: 4700160 | consumed tokens: 9625927680 | elapsed time per iteration (s): 0.78 | learning rate: 1.220E-04 | global batch size: 256 | lm loss: 2.165502E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.585 | TFLOPs: 19.94 | +31: iteration 18370/ 39672 | consumed samples: 4702720 | consumed tokens: 9631170560 | elapsed time per iteration (s): 0.83 | learning rate: 1.219E-04 | global batch size: 256 | lm loss: 2.224573E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.185 | TFLOPs: 18.77 | +31: iteration 18380/ 39672 | consumed samples: 4705280 | consumed tokens: 9636413440 | elapsed time per iteration (s): 0.75 | learning rate: 1.219E-04 | global batch size: 256 | lm loss: 2.194983E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.584 | TFLOPs: 20.60 | +31: iteration 18390/ 39672 | consumed samples: 4707840 | consumed tokens: 9641656320 | elapsed time per iteration (s): 0.81 | learning rate: 1.218E-04 | global batch size: 256 | lm loss: 2.213650E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.505 | TFLOPs: 19.15 | +31: iteration 18400/ 39672 | consumed samples: 4710400 | consumed tokens: 9646899200 | elapsed time per iteration (s): 0.81 | learning rate: 1.217E-04 | global batch size: 256 | lm loss: 2.183456E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.255 | TFLOPs: 19.07 | +31: iteration 18410/ 39672 | consumed samples: 4712960 | consumed tokens: 9652142080 | elapsed time per iteration (s): 0.90 | learning rate: 1.217E-04 | global batch size: 256 | lm loss: 2.162422E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 284.489 | TFLOPs: 17.21 | +31: iteration 18420/ 39672 | consumed samples: 4715520 | consumed tokens: 9657384960 | elapsed time per iteration (s): 0.82 | learning rate: 1.216E-04 | global batch size: 256 | lm loss: 2.187485E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.612 | TFLOPs: 18.91 | +31: iteration 18430/ 39672 | consumed samples: 4718080 | consumed tokens: 9662627840 | elapsed time per iteration (s): 0.82 | learning rate: 1.215E-04 | global batch size: 256 | lm loss: 2.203672E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.642 | TFLOPs: 18.91 | +31: iteration 18440/ 39672 | consumed samples: 4720640 | consumed tokens: 9667870720 | elapsed time per iteration (s): 0.79 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 2.210498E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.023 | TFLOPs: 19.72 | +31: iteration 18450/ 39672 | consumed samples: 4723200 | consumed tokens: 9673113600 | elapsed time per iteration (s): 0.74 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 2.173637E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.000 | TFLOPs: 20.93 | +31: iteration 18460/ 39672 | consumed samples: 4725760 | consumed tokens: 9678356480 | elapsed time per iteration (s): 0.81 | learning rate: 1.213E-04 | global batch size: 256 | lm loss: 2.160530E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.211 | TFLOPs: 19.19 | +31: iteration 18470/ 39672 | consumed samples: 4728320 | consumed tokens: 9683599360 | elapsed time per iteration (s): 0.80 | learning rate: 1.212E-04 | global batch size: 256 | lm loss: 2.180114E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.463 | TFLOPs: 19.27 | +31: iteration 18480/ 39672 | consumed samples: 4730880 | consumed tokens: 9688842240 | elapsed time per iteration (s): 0.83 | learning rate: 1.212E-04 | global batch size: 256 | lm loss: 2.168650E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.569 | TFLOPs: 18.67 | +31: iteration 18490/ 39672 | consumed samples: 4733440 | consumed tokens: 9694085120 | elapsed time per iteration (s): 0.83 | learning rate: 1.211E-04 | global batch size: 256 | lm loss: 2.185286E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.286 | TFLOPs: 18.59 | +31: iteration 18500/ 39672 | consumed samples: 4736000 | consumed tokens: 9699328000 | elapsed time per iteration (s): 0.82 | learning rate: 1.210E-04 | global batch size: 256 | lm loss: 2.194375E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.964 | TFLOPs: 18.87 | +31: iteration 18510/ 39672 | consumed samples: 4738560 | consumed tokens: 9704570880 | elapsed time per iteration (s): 0.80 | learning rate: 1.209E-04 | global batch size: 256 | lm loss: 2.181849E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.306 | TFLOPs: 19.38 | +31: iteration 18520/ 39672 | consumed samples: 4741120 | consumed tokens: 9709813760 | elapsed time per iteration (s): 0.80 | learning rate: 1.209E-04 | global batch size: 256 | lm loss: 2.160868E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.996 | TFLOPs: 19.42 | +31: iteration 18530/ 39672 | consumed samples: 4743680 | consumed tokens: 9715056640 | elapsed time per iteration (s): 0.79 | learning rate: 1.208E-04 | global batch size: 256 | lm loss: 2.185220E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.922 | TFLOPs: 19.60 | +31: iteration 18540/ 39672 | consumed samples: 4746240 | consumed tokens: 9720299520 | elapsed time per iteration (s): 0.79 | learning rate: 1.207E-04 | global batch size: 256 | lm loss: 2.203942E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.924 | TFLOPs: 19.54 | +31: iteration 18550/ 39672 | consumed samples: 4748800 | consumed tokens: 9725542400 | elapsed time per iteration (s): 0.81 | learning rate: 1.207E-04 | global batch size: 256 | lm loss: 2.205775E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.908 | TFLOPs: 19.23 | +31: iteration 18560/ 39672 | consumed samples: 4751360 | consumed tokens: 9730785280 | elapsed time per iteration (s): 0.79 | learning rate: 1.206E-04 | global batch size: 256 | lm loss: 2.197069E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.050 | TFLOPs: 19.73 | +31: iteration 18570/ 39672 | consumed samples: 4753920 | consumed tokens: 9736028160 | elapsed time per iteration (s): 0.80 | learning rate: 1.205E-04 | global batch size: 256 | lm loss: 2.160479E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.364 | TFLOPs: 19.32 | +31: iteration 18580/ 39672 | consumed samples: 4756480 | consumed tokens: 9741271040 | elapsed time per iteration (s): 0.77 | learning rate: 1.204E-04 | global batch size: 256 | lm loss: 2.201722E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.530 | TFLOPs: 20.00 | +31: iteration 18590/ 39672 | consumed samples: 4759040 | consumed tokens: 9746513920 | elapsed time per iteration (s): 0.78 | learning rate: 1.204E-04 | global batch size: 256 | lm loss: 2.178974E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.165 | TFLOPs: 19.91 | +31: iteration 18600/ 39672 | consumed samples: 4761600 | consumed tokens: 9751756800 | elapsed time per iteration (s): 0.78 | learning rate: 1.203E-04 | global batch size: 256 | lm loss: 2.177252E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.383 | TFLOPs: 19.93 | +31: iteration 18610/ 39672 | consumed samples: 4764160 | consumed tokens: 9756999680 | elapsed time per iteration (s): 0.80 | learning rate: 1.202E-04 | global batch size: 256 | lm loss: 2.194816E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.880 | TFLOPs: 19.29 | +31: iteration 18620/ 39672 | consumed samples: 4766720 | consumed tokens: 9762242560 | elapsed time per iteration (s): 0.74 | learning rate: 1.202E-04 | global batch size: 256 | lm loss: 2.187480E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.683 | TFLOPs: 20.91 | +31: iteration 18630/ 39672 | consumed samples: 4769280 | consumed tokens: 9767485440 | elapsed time per iteration (s): 0.75 | learning rate: 1.201E-04 | global batch size: 256 | lm loss: 2.197134E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.408 | TFLOPs: 20.78 | +31: iteration 18640/ 39672 | consumed samples: 4771840 | consumed tokens: 9772728320 | elapsed time per iteration (s): 0.81 | learning rate: 1.200E-04 | global batch size: 256 | lm loss: 2.187407E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.968 | TFLOPs: 19.12 | +31: iteration 18650/ 39672 | consumed samples: 4774400 | consumed tokens: 9777971200 | elapsed time per iteration (s): 0.78 | learning rate: 1.199E-04 | global batch size: 256 | lm loss: 2.185286E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.053 | TFLOPs: 19.79 | +31: iteration 18660/ 39672 | consumed samples: 4776960 | consumed tokens: 9783214080 | elapsed time per iteration (s): 0.73 | learning rate: 1.199E-04 | global batch size: 256 | lm loss: 2.208785E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.975 | TFLOPs: 21.35 | +31: iteration 18670/ 39672 | consumed samples: 4779520 | consumed tokens: 9788456960 | elapsed time per iteration (s): 0.76 | learning rate: 1.198E-04 | global batch size: 256 | lm loss: 2.164862E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.960 | TFLOPs: 20.45 | +31: iteration 18680/ 39672 | consumed samples: 4782080 | consumed tokens: 9793699840 | elapsed time per iteration (s): 0.80 | learning rate: 1.197E-04 | global batch size: 256 | lm loss: 2.229372E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.987 | TFLOPs: 19.36 | +31: iteration 18690/ 39672 | consumed samples: 4784640 | consumed tokens: 9798942720 | elapsed time per iteration (s): 0.82 | learning rate: 1.197E-04 | global batch size: 256 | lm loss: 2.182432E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.005 | TFLOPs: 19.00 | +31: iteration 18700/ 39672 | consumed samples: 4787200 | consumed tokens: 9804185600 | elapsed time per iteration (s): 0.75 | learning rate: 1.196E-04 | global batch size: 256 | lm loss: 2.191376E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.919 | TFLOPs: 20.56 | +31: iteration 18710/ 39672 | consumed samples: 4789760 | consumed tokens: 9809428480 | elapsed time per iteration (s): 0.81 | learning rate: 1.195E-04 | global batch size: 256 | lm loss: 2.201007E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.619 | TFLOPs: 19.22 | +31: iteration 18720/ 39672 | consumed samples: 4792320 | consumed tokens: 9814671360 | elapsed time per iteration (s): 0.74 | learning rate: 1.194E-04 | global batch size: 256 | lm loss: 2.189884E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.717 | TFLOPs: 20.85 | +31: iteration 18730/ 39672 | consumed samples: 4794880 | consumed tokens: 9819914240 | elapsed time per iteration (s): 0.75 | learning rate: 1.194E-04 | global batch size: 256 | lm loss: 2.188758E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.096 | TFLOPs: 20.70 | +31: iteration 18740/ 39672 | consumed samples: 4797440 | consumed tokens: 9825157120 | elapsed time per iteration (s): 0.76 | learning rate: 1.193E-04 | global batch size: 256 | lm loss: 2.197584E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.549 | TFLOPs: 20.42 | +31: iteration 18750/ 39672 | consumed samples: 4800000 | consumed tokens: 9830400000 | elapsed time per iteration (s): 0.77 | learning rate: 1.192E-04 | global batch size: 256 | lm loss: 2.189054E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.894 | TFLOPs: 20.14 | +31: iteration 18760/ 39672 | consumed samples: 4802560 | consumed tokens: 9835642880 | elapsed time per iteration (s): 0.80 | learning rate: 1.192E-04 | global batch size: 256 | lm loss: 2.205177E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.131 | TFLOPs: 19.25 | +31: iteration 18770/ 39672 | consumed samples: 4805120 | consumed tokens: 9840885760 | elapsed time per iteration (s): 0.76 | learning rate: 1.191E-04 | global batch size: 256 | lm loss: 2.150247E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.664 | TFLOPs: 20.49 | +31: iteration 18780/ 39672 | consumed samples: 4807680 | consumed tokens: 9846128640 | elapsed time per iteration (s): 0.77 | learning rate: 1.190E-04 | global batch size: 256 | lm loss: 2.208948E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.369 | TFLOPs: 20.05 | +31: iteration 18790/ 39672 | consumed samples: 4810240 | consumed tokens: 9851371520 | elapsed time per iteration (s): 0.78 | learning rate: 1.189E-04 | global batch size: 256 | lm loss: 2.184776E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.300 | TFLOPs: 19.86 | +31: iteration 18800/ 39672 | consumed samples: 4812800 | consumed tokens: 9856614400 | elapsed time per iteration (s): 0.74 | learning rate: 1.189E-04 | global batch size: 256 | lm loss: 2.192584E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.459 | TFLOPs: 20.90 | +31: iteration 18810/ 39672 | consumed samples: 4815360 | consumed tokens: 9861857280 | elapsed time per iteration (s): 0.73 | learning rate: 1.188E-04 | global batch size: 256 | lm loss: 2.155247E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.835 | TFLOPs: 21.22 | +31: iteration 18820/ 39672 | consumed samples: 4817920 | consumed tokens: 9867100160 | elapsed time per iteration (s): 0.71 | learning rate: 1.187E-04 | global batch size: 256 | lm loss: 2.196737E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 361.137 | TFLOPs: 21.85 | +31: iteration 18830/ 39672 | consumed samples: 4820480 | consumed tokens: 9872343040 | elapsed time per iteration (s): 0.73 | learning rate: 1.187E-04 | global batch size: 256 | lm loss: 2.189435E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.440 | TFLOPs: 21.08 | +31: iteration 18840/ 39672 | consumed samples: 4823040 | consumed tokens: 9877585920 | elapsed time per iteration (s): 0.76 | learning rate: 1.186E-04 | global batch size: 256 | lm loss: 2.153309E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.197 | TFLOPs: 20.46 | +31: iteration 18850/ 39672 | consumed samples: 4825600 | consumed tokens: 9882828800 | elapsed time per iteration (s): 0.73 | learning rate: 1.185E-04 | global batch size: 256 | lm loss: 2.181237E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.465 | TFLOPs: 21.14 | +31: iteration 18860/ 39672 | consumed samples: 4828160 | consumed tokens: 9888071680 | elapsed time per iteration (s): 0.71 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 2.179819E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 361.009 | TFLOPs: 21.84 | +31: iteration 18870/ 39672 | consumed samples: 4830720 | consumed tokens: 9893314560 | elapsed time per iteration (s): 0.74 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 2.188253E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.838 | TFLOPs: 20.80 | +31: iteration 18880/ 39672 | consumed samples: 4833280 | consumed tokens: 9898557440 | elapsed time per iteration (s): 0.81 | learning rate: 1.183E-04 | global batch size: 256 | lm loss: 2.184530E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.773 | TFLOPs: 19.10 | +31: iteration 18890/ 39672 | consumed samples: 4835840 | consumed tokens: 9903800320 | elapsed time per iteration (s): 0.81 | learning rate: 1.182E-04 | global batch size: 256 | lm loss: 2.203435E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.127 | TFLOPs: 19.00 | +31: iteration 18900/ 39672 | consumed samples: 4838400 | consumed tokens: 9909043200 | elapsed time per iteration (s): 0.83 | learning rate: 1.182E-04 | global batch size: 256 | lm loss: 2.175297E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.575 | TFLOPs: 18.73 | +31: iteration 18910/ 39672 | consumed samples: 4840960 | consumed tokens: 9914286080 | elapsed time per iteration (s): 0.82 | learning rate: 1.181E-04 | global batch size: 256 | lm loss: 2.189478E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.767 | TFLOPs: 18.92 | +31: iteration 18920/ 39672 | consumed samples: 4843520 | consumed tokens: 9919528960 | elapsed time per iteration (s): 0.82 | learning rate: 1.180E-04 | global batch size: 256 | lm loss: 2.163394E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.804 | TFLOPs: 18.92 | +31: iteration 18930/ 39672 | consumed samples: 4846080 | consumed tokens: 9924771840 | elapsed time per iteration (s): 0.82 | learning rate: 1.179E-04 | global batch size: 256 | lm loss: 2.179253E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.972 | TFLOPs: 18.93 | +31: iteration 18940/ 39672 | consumed samples: 4848640 | consumed tokens: 9930014720 | elapsed time per iteration (s): 0.75 | learning rate: 1.179E-04 | global batch size: 256 | lm loss: 2.221590E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.612 | TFLOPs: 20.61 | +31: iteration 18950/ 39672 | consumed samples: 4851200 | consumed tokens: 9935257600 | elapsed time per iteration (s): 0.76 | learning rate: 1.178E-04 | global batch size: 256 | lm loss: 2.179711E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.087 | TFLOPs: 20.45 | +31: iteration 18960/ 39672 | consumed samples: 4853760 | consumed tokens: 9940500480 | elapsed time per iteration (s): 0.74 | learning rate: 1.177E-04 | global batch size: 256 | lm loss: 2.152902E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.095 | TFLOPs: 21.06 | +31: iteration 18970/ 39672 | consumed samples: 4856320 | consumed tokens: 9945743360 | elapsed time per iteration (s): 0.74 | learning rate: 1.177E-04 | global batch size: 256 | lm loss: 2.202718E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.362 | TFLOPs: 21.01 | +31: iteration 18980/ 39672 | consumed samples: 4858880 | consumed tokens: 9950986240 | elapsed time per iteration (s): 0.78 | learning rate: 1.176E-04 | global batch size: 256 | lm loss: 2.200757E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.676 | TFLOPs: 19.82 | +31: iteration 18990/ 39672 | consumed samples: 4861440 | consumed tokens: 9956229120 | elapsed time per iteration (s): 0.74 | learning rate: 1.175E-04 | global batch size: 256 | lm loss: 2.191897E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.832 | TFLOPs: 20.92 | +31: iteration 19000/ 39672 | consumed samples: 4864000 | consumed tokens: 9961472000 | elapsed time per iteration (s): 0.76 | learning rate: 1.174E-04 | global batch size: 256 | lm loss: 2.204475E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.598 | TFLOPs: 20.48 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 19000 | lm loss value: 2.127891E+00 | lm loss PPL: 8.397137E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 19010/ 39672 | consumed samples: 4866560 | consumed tokens: 9966714880 | elapsed time per iteration (s): 0.74 | learning rate: 1.174E-04 | global batch size: 256 | lm loss: 2.207895E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.730 | TFLOPs: 20.92 | +31: iteration 19020/ 39672 | consumed samples: 4869120 | consumed tokens: 9971957760 | elapsed time per iteration (s): 0.73 | learning rate: 1.173E-04 | global batch size: 256 | lm loss: 2.202189E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.084 | TFLOPs: 21.12 | +31: iteration 19030/ 39672 | consumed samples: 4871680 | consumed tokens: 9977200640 | elapsed time per iteration (s): 0.73 | learning rate: 1.172E-04 | global batch size: 256 | lm loss: 2.168711E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.758 | TFLOPs: 21.10 | +31: iteration 19040/ 39672 | consumed samples: 4874240 | consumed tokens: 9982443520 | elapsed time per iteration (s): 0.74 | learning rate: 1.172E-04 | global batch size: 256 | lm loss: 2.204990E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.022 | TFLOPs: 20.99 | +31: iteration 19050/ 39672 | consumed samples: 4876800 | consumed tokens: 9987686400 | elapsed time per iteration (s): 0.77 | learning rate: 1.171E-04 | global batch size: 256 | lm loss: 2.173542E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.092 | TFLOPs: 20.03 | +31: iteration 19060/ 39672 | consumed samples: 4879360 | consumed tokens: 9992929280 | elapsed time per iteration (s): 0.81 | learning rate: 1.170E-04 | global batch size: 256 | lm loss: 2.172449E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.564 | TFLOPs: 19.09 | +31: iteration 19070/ 39672 | consumed samples: 4881920 | consumed tokens: 9998172160 | elapsed time per iteration (s): 0.81 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 2.161105E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.727 | TFLOPs: 19.16 | +31: iteration 19080/ 39672 | consumed samples: 4884480 | consumed tokens: 10003415040 | elapsed time per iteration (s): 0.82 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 2.189771E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.632 | TFLOPs: 18.85 | +31: iteration 19090/ 39672 | consumed samples: 4887040 | consumed tokens: 10008657920 | elapsed time per iteration (s): 0.87 | learning rate: 1.168E-04 | global batch size: 256 | lm loss: 2.208357E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 293.519 | TFLOPs: 17.76 | +31: iteration 19100/ 39672 | consumed samples: 4889600 | consumed tokens: 10013900800 | elapsed time per iteration (s): 0.81 | learning rate: 1.167E-04 | global batch size: 256 | lm loss: 2.209727E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.922 | TFLOPs: 19.17 | +31: iteration 19110/ 39672 | consumed samples: 4892160 | consumed tokens: 10019143680 | elapsed time per iteration (s): 0.81 | learning rate: 1.167E-04 | global batch size: 256 | lm loss: 2.214414E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.922 | TFLOPs: 19.23 | +31: iteration 19120/ 39672 | consumed samples: 4894720 | consumed tokens: 10024386560 | elapsed time per iteration (s): 0.77 | learning rate: 1.166E-04 | global batch size: 256 | lm loss: 2.177000E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.506 | TFLOPs: 19.99 | +31: iteration 19130/ 39672 | consumed samples: 4897280 | consumed tokens: 10029629440 | elapsed time per iteration (s): 0.86 | learning rate: 1.165E-04 | global batch size: 256 | lm loss: 2.169870E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.320 | TFLOPs: 18.11 | +31: iteration 19140/ 39672 | consumed samples: 4899840 | consumed tokens: 10034872320 | elapsed time per iteration (s): 0.79 | learning rate: 1.164E-04 | global batch size: 256 | lm loss: 2.173125E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.183 | TFLOPs: 19.49 | +31: iteration 19150/ 39672 | consumed samples: 4902400 | consumed tokens: 10040115200 | elapsed time per iteration (s): 0.83 | learning rate: 1.164E-04 | global batch size: 256 | lm loss: 2.168624E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.168 | TFLOPs: 18.70 | +31: iteration 19160/ 39672 | consumed samples: 4904960 | consumed tokens: 10045358080 | elapsed time per iteration (s): 0.84 | learning rate: 1.163E-04 | global batch size: 256 | lm loss: 2.193571E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.195 | TFLOPs: 18.34 | +31: iteration 19170/ 39672 | consumed samples: 4907520 | consumed tokens: 10050600960 | elapsed time per iteration (s): 0.81 | learning rate: 1.162E-04 | global batch size: 256 | lm loss: 2.170606E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.517 | TFLOPs: 19.21 | +31: iteration 19180/ 39672 | consumed samples: 4910080 | consumed tokens: 10055843840 | elapsed time per iteration (s): 0.75 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 2.187727E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.088 | TFLOPs: 20.70 | +31: iteration 19190/ 39672 | consumed samples: 4912640 | consumed tokens: 10061086720 | elapsed time per iteration (s): 0.78 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 2.187414E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.380 | TFLOPs: 19.81 | +31: iteration 19200/ 39672 | consumed samples: 4915200 | consumed tokens: 10066329600 | elapsed time per iteration (s): 0.80 | learning rate: 1.160E-04 | global batch size: 256 | lm loss: 2.189309E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.442 | TFLOPs: 19.33 | +31: iteration 19210/ 39672 | consumed samples: 4917760 | consumed tokens: 10071572480 | elapsed time per iteration (s): 0.80 | learning rate: 1.159E-04 | global batch size: 256 | lm loss: 2.178406E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.158 | TFLOPs: 19.43 | +31: iteration 19220/ 39672 | consumed samples: 4920320 | consumed tokens: 10076815360 | elapsed time per iteration (s): 0.81 | learning rate: 1.159E-04 | global batch size: 256 | lm loss: 2.183632E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.316 | TFLOPs: 19.02 | +31: iteration 19230/ 39672 | consumed samples: 4922880 | consumed tokens: 10082058240 | elapsed time per iteration (s): 0.79 | learning rate: 1.158E-04 | global batch size: 256 | lm loss: 2.183451E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.193 | TFLOPs: 19.49 | +31: iteration 19240/ 39672 | consumed samples: 4925440 | consumed tokens: 10087301120 | elapsed time per iteration (s): 0.80 | learning rate: 1.157E-04 | global batch size: 256 | lm loss: 2.188632E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.594 | TFLOPs: 19.33 | +31: iteration 19250/ 39672 | consumed samples: 4928000 | consumed tokens: 10092544000 | elapsed time per iteration (s): 0.78 | learning rate: 1.156E-04 | global batch size: 256 | lm loss: 2.211100E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.709 | TFLOPs: 19.89 | +31: iteration 19260/ 39672 | consumed samples: 4930560 | consumed tokens: 10097786880 | elapsed time per iteration (s): 0.81 | learning rate: 1.156E-04 | global batch size: 256 | lm loss: 2.175319E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.397 | TFLOPs: 19.14 | +31: iteration 19270/ 39672 | consumed samples: 4933120 | consumed tokens: 10103029760 | elapsed time per iteration (s): 0.82 | learning rate: 1.155E-04 | global batch size: 256 | lm loss: 2.157047E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.108 | TFLOPs: 19.00 | +31: iteration 19280/ 39672 | consumed samples: 4935680 | consumed tokens: 10108272640 | elapsed time per iteration (s): 0.83 | learning rate: 1.154E-04 | global batch size: 256 | lm loss: 2.175397E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.361 | TFLOPs: 18.72 | +31: iteration 19290/ 39672 | consumed samples: 4938240 | consumed tokens: 10113515520 | elapsed time per iteration (s): 0.82 | learning rate: 1.154E-04 | global batch size: 256 | lm loss: 2.190288E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.405 | TFLOPs: 18.78 | +31: iteration 19300/ 39672 | consumed samples: 4940800 | consumed tokens: 10118758400 | elapsed time per iteration (s): 0.82 | learning rate: 1.153E-04 | global batch size: 256 | lm loss: 2.179431E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.940 | TFLOPs: 18.99 | +31: iteration 19310/ 39672 | consumed samples: 4943360 | consumed tokens: 10124001280 | elapsed time per iteration (s): 0.79 | learning rate: 1.152E-04 | global batch size: 256 | lm loss: 2.171358E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.768 | TFLOPs: 19.59 | +31: iteration 19320/ 39672 | consumed samples: 4945920 | consumed tokens: 10129244160 | elapsed time per iteration (s): 0.78 | learning rate: 1.151E-04 | global batch size: 256 | lm loss: 2.161747E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.907 | TFLOPs: 19.96 | +31: iteration 19330/ 39672 | consumed samples: 4948480 | consumed tokens: 10134487040 | elapsed time per iteration (s): 0.78 | learning rate: 1.151E-04 | global batch size: 256 | lm loss: 2.158280E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.758 | TFLOPs: 19.77 | +31: iteration 19340/ 39672 | consumed samples: 4951040 | consumed tokens: 10139729920 | elapsed time per iteration (s): 0.83 | learning rate: 1.150E-04 | global batch size: 256 | lm loss: 2.183819E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.674 | TFLOPs: 18.61 | +31: iteration 19350/ 39672 | consumed samples: 4953600 | consumed tokens: 10144972800 | elapsed time per iteration (s): 0.81 | learning rate: 1.149E-04 | global batch size: 256 | lm loss: 2.175377E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.056 | TFLOPs: 19.12 | +31: iteration 19360/ 39672 | consumed samples: 4956160 | consumed tokens: 10150215680 | elapsed time per iteration (s): 0.81 | learning rate: 1.149E-04 | global batch size: 256 | lm loss: 2.169441E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.184 | TFLOPs: 19.01 | +31: iteration 19370/ 39672 | consumed samples: 4958720 | consumed tokens: 10155458560 | elapsed time per iteration (s): 0.79 | learning rate: 1.148E-04 | global batch size: 256 | lm loss: 2.172622E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.270 | TFLOPs: 19.62 | +31: iteration 19380/ 39672 | consumed samples: 4961280 | consumed tokens: 10160701440 | elapsed time per iteration (s): 0.80 | learning rate: 1.147E-04 | global batch size: 256 | lm loss: 2.156325E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.089 | TFLOPs: 19.24 | +31: iteration 19390/ 39672 | consumed samples: 4963840 | consumed tokens: 10165944320 | elapsed time per iteration (s): 0.84 | learning rate: 1.146E-04 | global batch size: 256 | lm loss: 2.181233E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.984 | TFLOPs: 18.39 | +31: iteration 19400/ 39672 | consumed samples: 4966400 | consumed tokens: 10171187200 | elapsed time per iteration (s): 0.84 | learning rate: 1.146E-04 | global batch size: 256 | lm loss: 2.180881E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.116 | TFLOPs: 18.46 | +31: iteration 19410/ 39672 | consumed samples: 4968960 | consumed tokens: 10176430080 | elapsed time per iteration (s): 0.84 | learning rate: 1.145E-04 | global batch size: 256 | lm loss: 2.182092E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.618 | TFLOPs: 18.49 | +31: iteration 19420/ 39672 | consumed samples: 4971520 | consumed tokens: 10181672960 | elapsed time per iteration (s): 0.82 | learning rate: 1.144E-04 | global batch size: 256 | lm loss: 2.189185E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.603 | TFLOPs: 18.85 | +31: iteration 19430/ 39672 | consumed samples: 4974080 | consumed tokens: 10186915840 | elapsed time per iteration (s): 0.82 | learning rate: 1.144E-04 | global batch size: 256 | lm loss: 2.199430E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.498 | TFLOPs: 18.91 | +31: iteration 19440/ 39672 | consumed samples: 4976640 | consumed tokens: 10192158720 | elapsed time per iteration (s): 0.78 | learning rate: 1.143E-04 | global batch size: 256 | lm loss: 2.183206E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.559 | TFLOPs: 19.76 | +31: iteration 19450/ 39672 | consumed samples: 4979200 | consumed tokens: 10197401600 | elapsed time per iteration (s): 0.86 | learning rate: 1.142E-04 | global batch size: 256 | lm loss: 2.197208E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.856 | TFLOPs: 17.96 | +31: iteration 19460/ 39672 | consumed samples: 4981760 | consumed tokens: 10202644480 | elapsed time per iteration (s): 0.79 | learning rate: 1.141E-04 | global batch size: 256 | lm loss: 2.170581E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.547 | TFLOPs: 19.63 | +31: iteration 19470/ 39672 | consumed samples: 4984320 | consumed tokens: 10207887360 | elapsed time per iteration (s): 0.84 | learning rate: 1.141E-04 | global batch size: 256 | lm loss: 2.155927E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.085 | TFLOPs: 18.40 | +31: iteration 19480/ 39672 | consumed samples: 4986880 | consumed tokens: 10213130240 | elapsed time per iteration (s): 0.84 | learning rate: 1.140E-04 | global batch size: 256 | lm loss: 2.163690E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.147 | TFLOPs: 18.34 | +31: iteration 19490/ 39672 | consumed samples: 4989440 | consumed tokens: 10218373120 | elapsed time per iteration (s): 0.86 | learning rate: 1.139E-04 | global batch size: 256 | lm loss: 2.181737E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.005 | TFLOPs: 17.91 | +31: iteration 19500/ 39672 | consumed samples: 4992000 | consumed tokens: 10223616000 | elapsed time per iteration (s): 0.86 | learning rate: 1.138E-04 | global batch size: 256 | lm loss: 2.166501E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.643 | TFLOPs: 17.95 | +31: iteration 19510/ 39672 | consumed samples: 4994560 | consumed tokens: 10228858880 | elapsed time per iteration (s): 0.83 | learning rate: 1.138E-04 | global batch size: 256 | lm loss: 2.191802E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.822 | TFLOPs: 18.68 | +31: iteration 19520/ 39672 | consumed samples: 4997120 | consumed tokens: 10234101760 | elapsed time per iteration (s): 0.82 | learning rate: 1.137E-04 | global batch size: 256 | lm loss: 2.189939E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.561 | TFLOPs: 18.85 | +31: iteration 19530/ 39672 | consumed samples: 4999680 | consumed tokens: 10239344640 | elapsed time per iteration (s): 0.83 | learning rate: 1.136E-04 | global batch size: 256 | lm loss: 2.163125E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.414 | TFLOPs: 18.60 | +31: iteration 19540/ 39672 | consumed samples: 5002240 | consumed tokens: 10244587520 | elapsed time per iteration (s): 0.79 | learning rate: 1.136E-04 | global batch size: 256 | lm loss: 2.182267E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.621 | TFLOPs: 19.64 | +31: iteration 19550/ 39672 | consumed samples: 5004800 | consumed tokens: 10249830400 | elapsed time per iteration (s): 0.82 | learning rate: 1.135E-04 | global batch size: 256 | lm loss: 2.204725E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.993 | TFLOPs: 18.81 | +31: iteration 19560/ 39672 | consumed samples: 5007360 | consumed tokens: 10255073280 | elapsed time per iteration (s): 0.77 | learning rate: 1.134E-04 | global batch size: 256 | lm loss: 2.172337E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.846 | TFLOPs: 20.02 | +31: iteration 19570/ 39672 | consumed samples: 5009920 | consumed tokens: 10260316160 | elapsed time per iteration (s): 0.82 | learning rate: 1.133E-04 | global batch size: 256 | lm loss: 2.160459E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.821 | TFLOPs: 18.86 | +31: iteration 19580/ 39672 | consumed samples: 5012480 | consumed tokens: 10265559040 | elapsed time per iteration (s): 0.74 | learning rate: 1.133E-04 | global batch size: 256 | lm loss: 2.184021E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.793 | TFLOPs: 20.86 | +31: iteration 19590/ 39672 | consumed samples: 5015040 | consumed tokens: 10270801920 | elapsed time per iteration (s): 0.80 | learning rate: 1.132E-04 | global batch size: 256 | lm loss: 2.157348E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.341 | TFLOPs: 19.44 | +31: iteration 19600/ 39672 | consumed samples: 5017600 | consumed tokens: 10276044800 | elapsed time per iteration (s): 0.76 | learning rate: 1.131E-04 | global batch size: 256 | lm loss: 2.151771E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.578 | TFLOPs: 20.36 | +31: iteration 19610/ 39672 | consumed samples: 5020160 | consumed tokens: 10281287680 | elapsed time per iteration (s): 0.77 | learning rate: 1.131E-04 | global batch size: 256 | lm loss: 2.181720E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.587 | TFLOPs: 20.18 | +31: iteration 19620/ 39672 | consumed samples: 5022720 | consumed tokens: 10286530560 | elapsed time per iteration (s): 0.77 | learning rate: 1.130E-04 | global batch size: 256 | lm loss: 2.187560E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.411 | TFLOPs: 20.17 | +31: iteration 19630/ 39672 | consumed samples: 5025280 | consumed tokens: 10291773440 | elapsed time per iteration (s): 0.79 | learning rate: 1.129E-04 | global batch size: 256 | lm loss: 2.185641E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.633 | TFLOPs: 19.58 | +31: iteration 19640/ 39672 | consumed samples: 5027840 | consumed tokens: 10297016320 | elapsed time per iteration (s): 0.79 | learning rate: 1.128E-04 | global batch size: 256 | lm loss: 2.199835E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.291 | TFLOPs: 19.62 | +31: iteration 19650/ 39672 | consumed samples: 5030400 | consumed tokens: 10302259200 | elapsed time per iteration (s): 0.82 | learning rate: 1.128E-04 | global batch size: 256 | lm loss: 2.149088E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.391 | TFLOPs: 18.78 | +31: iteration 19660/ 39672 | consumed samples: 5032960 | consumed tokens: 10307502080 | elapsed time per iteration (s): 0.85 | learning rate: 1.127E-04 | global batch size: 256 | lm loss: 2.179501E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.678 | TFLOPs: 18.19 | +31: iteration 19670/ 39672 | consumed samples: 5035520 | consumed tokens: 10312744960 | elapsed time per iteration (s): 0.73 | learning rate: 1.126E-04 | global batch size: 256 | lm loss: 2.164655E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.983 | TFLOPs: 21.23 | +31: iteration 19680/ 39672 | consumed samples: 5038080 | consumed tokens: 10317987840 | elapsed time per iteration (s): 0.77 | learning rate: 1.126E-04 | global batch size: 256 | lm loss: 2.155736E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.835 | TFLOPs: 20.08 | +31: iteration 19690/ 39672 | consumed samples: 5040640 | consumed tokens: 10323230720 | elapsed time per iteration (s): 0.76 | learning rate: 1.125E-04 | global batch size: 256 | lm loss: 2.161752E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.122 | TFLOPs: 20.27 | +31: iteration 19700/ 39672 | consumed samples: 5043200 | consumed tokens: 10328473600 | elapsed time per iteration (s): 0.96 | learning rate: 1.124E-04 | global batch size: 256 | lm loss: 2.170838E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 266.192 | TFLOPs: 16.10 | +31: iteration 19710/ 39672 | consumed samples: 5045760 | consumed tokens: 10333716480 | elapsed time per iteration (s): 1.00 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 2.164072E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 255.871 | TFLOPs: 15.48 | +31: iteration 19720/ 39672 | consumed samples: 5048320 | consumed tokens: 10338959360 | elapsed time per iteration (s): 0.81 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 2.151587E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.214 | TFLOPs: 19.19 | +31: iteration 19730/ 39672 | consumed samples: 5050880 | consumed tokens: 10344202240 | elapsed time per iteration (s): 0.77 | learning rate: 1.122E-04 | global batch size: 256 | lm loss: 2.168668E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.140 | TFLOPs: 20.03 | +31: iteration 19740/ 39672 | consumed samples: 5053440 | consumed tokens: 10349445120 | elapsed time per iteration (s): 0.77 | learning rate: 1.121E-04 | global batch size: 256 | lm loss: 2.200137E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.538 | TFLOPs: 20.24 | +31: iteration 19750/ 39672 | consumed samples: 5056000 | consumed tokens: 10354688000 | elapsed time per iteration (s): 0.79 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 2.175359E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.893 | TFLOPs: 19.53 | +31: iteration 19760/ 39672 | consumed samples: 5058560 | consumed tokens: 10359930880 | elapsed time per iteration (s): 0.78 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 2.167867E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.596 | TFLOPs: 19.94 | +31: iteration 19770/ 39672 | consumed samples: 5061120 | consumed tokens: 10365173760 | elapsed time per iteration (s): 0.76 | learning rate: 1.119E-04 | global batch size: 256 | lm loss: 2.175474E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.642 | TFLOPs: 20.43 | +31: iteration 19780/ 39672 | consumed samples: 5063680 | consumed tokens: 10370416640 | elapsed time per iteration (s): 0.80 | learning rate: 1.118E-04 | global batch size: 256 | lm loss: 2.184565E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.166 | TFLOPs: 19.37 | +31: iteration 19790/ 39672 | consumed samples: 5066240 | consumed tokens: 10375659520 | elapsed time per iteration (s): 1.08 | learning rate: 1.118E-04 | global batch size: 256 | lm loss: 2.174867E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 237.069 | TFLOPs: 14.34 | +31: iteration 19800/ 39672 | consumed samples: 5068800 | consumed tokens: 10380902400 | elapsed time per iteration (s): 0.81 | learning rate: 1.117E-04 | global batch size: 256 | lm loss: 2.148561E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.886 | TFLOPs: 19.11 | +31: iteration 19810/ 39672 | consumed samples: 5071360 | consumed tokens: 10386145280 | elapsed time per iteration (s): 0.76 | learning rate: 1.116E-04 | global batch size: 256 | lm loss: 2.180738E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.945 | TFLOPs: 20.26 | +31: iteration 19820/ 39672 | consumed samples: 5073920 | consumed tokens: 10391388160 | elapsed time per iteration (s): 0.75 | learning rate: 1.115E-04 | global batch size: 256 | lm loss: 2.175377E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.746 | TFLOPs: 20.74 | +31: iteration 19830/ 39672 | consumed samples: 5076480 | consumed tokens: 10396631040 | elapsed time per iteration (s): 0.80 | learning rate: 1.115E-04 | global batch size: 256 | lm loss: 2.148857E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.251 | TFLOPs: 19.25 | +31: iteration 19840/ 39672 | consumed samples: 5079040 | consumed tokens: 10401873920 | elapsed time per iteration (s): 0.76 | learning rate: 1.114E-04 | global batch size: 256 | lm loss: 2.155417E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.174 | TFLOPs: 20.34 | +31: iteration 19850/ 39672 | consumed samples: 5081600 | consumed tokens: 10407116800 | elapsed time per iteration (s): 0.77 | learning rate: 1.113E-04 | global batch size: 256 | lm loss: 2.191623E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.377 | TFLOPs: 20.11 | +31: iteration 19860/ 39672 | consumed samples: 5084160 | consumed tokens: 10412359680 | elapsed time per iteration (s): 0.77 | learning rate: 1.113E-04 | global batch size: 256 | lm loss: 2.187032E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.757 | TFLOPs: 20.13 | +31: iteration 19870/ 39672 | consumed samples: 5086720 | consumed tokens: 10417602560 | elapsed time per iteration (s): 0.73 | learning rate: 1.112E-04 | global batch size: 256 | lm loss: 2.194764E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.810 | TFLOPs: 21.34 | +31: iteration 19880/ 39672 | consumed samples: 5089280 | consumed tokens: 10422845440 | elapsed time per iteration (s): 0.76 | learning rate: 1.111E-04 | global batch size: 256 | lm loss: 2.171902E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.096 | TFLOPs: 20.33 | +31: iteration 19890/ 39672 | consumed samples: 5091840 | consumed tokens: 10428088320 | elapsed time per iteration (s): 0.73 | learning rate: 1.110E-04 | global batch size: 256 | lm loss: 2.171323E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.950 | TFLOPs: 21.35 | +31: iteration 19900/ 39672 | consumed samples: 5094400 | consumed tokens: 10433331200 | elapsed time per iteration (s): 0.79 | learning rate: 1.110E-04 | global batch size: 256 | lm loss: 2.175865E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.590 | TFLOPs: 19.64 | +31: iteration 19910/ 39672 | consumed samples: 5096960 | consumed tokens: 10438574080 | elapsed time per iteration (s): 0.77 | learning rate: 1.109E-04 | global batch size: 256 | lm loss: 2.191896E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.406 | TFLOPs: 20.05 | +31: iteration 19920/ 39672 | consumed samples: 5099520 | consumed tokens: 10443816960 | elapsed time per iteration (s): 0.73 | learning rate: 1.108E-04 | global batch size: 256 | lm loss: 2.197454E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.175 | TFLOPs: 21.25 | +31: iteration 19930/ 39672 | consumed samples: 5102080 | consumed tokens: 10449059840 | elapsed time per iteration (s): 0.76 | learning rate: 1.108E-04 | global batch size: 256 | lm loss: 2.139794E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.137 | TFLOPs: 20.27 | +31: iteration 19940/ 39672 | consumed samples: 5104640 | consumed tokens: 10454302720 | elapsed time per iteration (s): 0.92 | learning rate: 1.107E-04 | global batch size: 256 | lm loss: 2.197787E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 278.534 | TFLOPs: 16.85 | +31: iteration 19950/ 39672 | consumed samples: 5107200 | consumed tokens: 10459545600 | elapsed time per iteration (s): 0.73 | learning rate: 1.106E-04 | global batch size: 256 | lm loss: 2.151211E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.131 | TFLOPs: 21.24 | +31: iteration 19960/ 39672 | consumed samples: 5109760 | consumed tokens: 10464788480 | elapsed time per iteration (s): 0.78 | learning rate: 1.105E-04 | global batch size: 256 | lm loss: 2.148012E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.936 | TFLOPs: 19.90 | +31: iteration 19970/ 39672 | consumed samples: 5112320 | consumed tokens: 10470031360 | elapsed time per iteration (s): 0.79 | learning rate: 1.105E-04 | global batch size: 256 | lm loss: 2.185838E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.178 | TFLOPs: 19.67 | +31: iteration 19980/ 39672 | consumed samples: 5114880 | consumed tokens: 10475274240 | elapsed time per iteration (s): 0.78 | learning rate: 1.104E-04 | global batch size: 256 | lm loss: 2.191148E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.774 | TFLOPs: 19.77 | +31: iteration 19990/ 39672 | consumed samples: 5117440 | consumed tokens: 10480517120 | elapsed time per iteration (s): 0.79 | learning rate: 1.103E-04 | global batch size: 256 | lm loss: 2.185670E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.939 | TFLOPs: 19.72 | + 0: [2022-11-30 13:38:18,847] [INFO] [logging.py:68:log_dist] [Rank 0] step=20000, skipped=0, lr=[0.00011025045536444024, 0.00011025045536444024, 0.00011025045536444024], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 20000/ 39672 | consumed samples: 5120000 | consumed tokens: 10485760000 | elapsed time per iteration (s): 0.78 | learning rate: 1.103E-04 | global batch size: 256 | lm loss: 2.202655E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.615 | TFLOPs: 19.76 | + 0: steps: 20000 loss: 2.1712 iter time (s): 0.785 samples/sec: 326.148 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 20000 | lm loss value: 2.091009E+00 | lm loss PPL: 8.093078E+00 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 20000 to checkpoints_1b121b + 0: [2022-11-30 13:38:19,295] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step20000 is begin to save! + 0: [2022-11-30 13:38:19,363] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_01-model_00-model_states.pt... + 0: [2022-11-30 13:38:19,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_01-model_00-model_states.pt. + 0: [2022-11-30 13:38:19,745] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_03-model_00-model_states.pt... + 0: [2022-11-30 13:38:19,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_03-model_00-model_states.pt. + 0: [2022-11-30 13:38:19,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_04-model_00-model_states.pt... + 0: [2022-11-30 13:38:19,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_04-model_00-model_states.pt. + 0: [2022-11-30 13:38:19,912] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_05-model_00-model_states.pt... + 0: [2022-11-30 13:38:19,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_05-model_00-model_states.pt. + 0: [2022-11-30 13:38:19,994] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_06-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_06-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,073] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_07-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_07-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_08-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_08-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,233] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_09-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_09-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,312] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_10-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_10-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_11-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_11-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,465] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_12-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_12-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_13-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_13-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_14-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_14-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,691] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_15-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_15-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,767] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_16-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_16-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,843] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_17-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_17-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,917] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_18-model_00-model_states.pt... + 0: [2022-11-30 13:38:20,988] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_18-model_00-model_states.pt. + 0: [2022-11-30 13:38:20,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_19-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_19-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_20-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_20-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,137] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_21-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_21-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,210] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_22-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_22-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,284] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_23-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_23-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_24-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_24-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,430] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_25-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_25-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_26-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_26-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,580] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_27-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_27-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,652] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_28-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_28-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,727] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/layer_30-model_00-model_states.pt... + 0: [2022-11-30 13:38:21,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/layer_30-model_00-model_states.pt. + 0: [2022-11-30 13:38:21,729] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_1b121b/global_step20000/mp_rank_00_model_states.pt + 0: [2022-11-30 13:38:21,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/mp_rank_00_model_states.pt... + 0: [2022-11-30 13:38:21,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/mp_rank_00_model_states.pt. + 0: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 3: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +31: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +20: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +26: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... + 4: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +28: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... + 0: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +19: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +12: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... + 8: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 3: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +23: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +21: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 5: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +30: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +10: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... + 6: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +27: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +31: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 7: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 9: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +11: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +20: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +17: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +22: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +26: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +16: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +15: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... + 4: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +14: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +18: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +28: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... + 0: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +19: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +12: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... + 8: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 3: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +23: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +21: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +29: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +24: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... + 5: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +13: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +30: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +10: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... + 6: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +27: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +31: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 7: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 9: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +11: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +20: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +17: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +22: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +26: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +16: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... + 1: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +15: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... + 2: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 4: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +14: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +18: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +28: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... + 0: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +19: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +12: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... + 8: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 3: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +23: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +21: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +29: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +24: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... + 5: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +13: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +30: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +10: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... + 6: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +27: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +25: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +31: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 7: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 9: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +11: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +20: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +17: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +22: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +26: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +16: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... + 1: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +15: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... + 2: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 4: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +14: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +18: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +28: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... + 0: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +19: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +12: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... + 8: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 3: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +21: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +29: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +24: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +13: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +30: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +10: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +25: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +31: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 7: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +20: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +22: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +26: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... + 1: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +15: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... + 2: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 4: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +14: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +18: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +19: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... + 3: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +13: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +25: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +20: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +22: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +26: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +18: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-30 13:38:21,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... + 0: [2022-11-30 13:38:21,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-30 13:38:21,874] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-30 13:38:21,874] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-30 13:38:21,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-30 13:38:21,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-30 13:38:21,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-30 13:38:21,882] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-30 13:38:21,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-30 13:38:21,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-30 13:38:21,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-30 13:38:21,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-30 13:38:21,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-30 13:38:21,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-30 13:38:21,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-30 13:38:21,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-30 13:38:21,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-30 13:38:21,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-30 13:38:21,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-30 13:38:21,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-30 13:38:21,893] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-30 13:38:21,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-30 13:38:21,896] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-30 13:38:21,896] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-30 13:38:21,896] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-30 13:38:21,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-30 13:38:21,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-30 13:38:21,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-30 13:38:21,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-30 13:38:21,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-30 13:38:21,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-30 13:38:21,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-30 13:38:21,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-30 13:38:21,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-30 13:38:21,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-30 13:38:21,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-30 13:38:21,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-30 13:38:21,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-30 13:38:21,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-30 13:38:21,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-30 13:38:21,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +24: [2022-11-30 13:38:21,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-30 13:38:21,906] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-30 13:38:21,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-30 13:38:21,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +25: [2022-11-30 13:38:21,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-30 13:38:21,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-30 13:38:21,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-30 13:38:21,905] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-30 13:38:21,905] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-30 13:38:21,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-30 13:38:21,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-30 13:38:21,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-30 13:38:21,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-30 13:38:21,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-30 13:38:21,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-30 13:38:21,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-30 13:38:21,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-30 13:38:21,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-30 13:38:21,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-30 13:38:21,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-30 13:38:21,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-30 13:38:21,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-30 13:38:21,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-30 13:38:21,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-30 13:38:21,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-30 13:38:21,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-30 13:38:21,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-30 13:38:21,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-30 13:38:21,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-30 13:38:21,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-30 13:38:21,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-30 13:38:21,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-30 13:38:21,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-30 13:38:21,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-30 13:38:21,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-30 13:38:21,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-30 13:38:21,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-30 13:38:21,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-30 13:38:21,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-30 13:38:21,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-30 13:38:21,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 0: [2022-11-30 13:38:21,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-30 13:38:21,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-30 13:38:21,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-30 13:38:21,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-30 13:38:21,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-30 13:38:21,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-30 13:38:21,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +30: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-30 13:38:21,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt + 0: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-30 13:38:21,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +30: [2022-11-30 13:38:21,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +11: [2022-11-30 13:38:21,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-30 13:38:21,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-30 13:38:21,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-30 13:38:21,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +11: [2022-11-30 13:38:21,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-30 13:38:21,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-30 13:38:21,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-30 13:38:21,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-30 13:38:21,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-30 13:38:21,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-30 13:38:21,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-30 13:38:21,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-30 13:38:21,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-30 13:38:21,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-30 13:38:21,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-30 13:38:21,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-30 13:38:21,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-30 13:38:21,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-30 13:38:21,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-30 13:38:21,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-30 13:38:21,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-30 13:38:21,927] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-30 13:38:21,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-30 13:38:21,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-30 13:38:21,927] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-30 13:38:21,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-30 13:38:21,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-30 13:38:21,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-30 13:38:21,928] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-30 13:38:21,928] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-30 13:38:21,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-30 13:38:21,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-30 13:38:21,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-30 13:38:21,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-30 13:38:21,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-30 13:38:21,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-30 13:38:21,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-30 13:38:21,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-30 13:38:21,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-30 13:38:21,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-30 13:38:21,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-30 13:38:21,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-30 13:38:21,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-30 13:38:21,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-30 13:38:21,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-30 13:38:21,934] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-30 13:38:21,934] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-30 13:38:21,934] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-30 13:38:21,934] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-30 13:38:21,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-30 13:38:21,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-30 13:38:21,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-30 13:38:21,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-30 13:38:21,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-30 13:38:21,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-30 13:38:21,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-30 13:38:21,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-30 13:38:21,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-30 13:38:21,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-30 13:38:21,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-30 13:38:21,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-30 13:38:21,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-30 13:38:21,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-30 13:38:21,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-30 13:38:21,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-30 13:38:21,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-30 13:38:21,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-30 13:38:21,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-30 13:38:21,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 1: [2022-11-30 13:38:21,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 5: [2022-11-30 13:38:21,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-30 13:38:21,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-30 13:38:21,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-30 13:38:21,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. + 1: [2022-11-30 13:38:21,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +27: [2022-11-30 13:38:21,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-30 13:38:21,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-30 13:38:21,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt + 1: [2022-11-30 13:38:21,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-30 13:38:21,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-30 13:38:21,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-30 13:38:21,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-30 13:38:21,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-30 13:38:21,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-30 13:38:21,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-30 13:38:21,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-30 13:38:21,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 2: [2022-11-30 13:38:21,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 5: [2022-11-30 13:38:21,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-30 13:38:21,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 2: [2022-11-30 13:38:21,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 5: [2022-11-30 13:38:21,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-30 13:38:21,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-30 13:38:21,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-30 13:38:21,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-30 13:38:21,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-30 13:38:21,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-30 13:38:21,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-30 13:38:21,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-30 13:38:21,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-30 13:38:21,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. + 8: [2022-11-30 13:38:21,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-30 13:38:21,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-30 13:38:21,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +17: [2022-11-30 13:38:21,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. + 8: [2022-11-30 13:38:21,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-30 13:38:21,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-30 13:38:21,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +17: [2022-11-30 13:38:21,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-30 13:38:21,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt + 8: [2022-11-30 13:38:21,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-30 13:38:21,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-30 13:38:21,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-30 13:38:21,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-30 13:38:21,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-30 13:38:21,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-30 13:38:21,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-30 13:38:21,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-30 13:38:21,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-30 13:38:21,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-30 13:38:21,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-30 13:38:21,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-30 13:38:21,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-30 13:38:21,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-30 13:38:21,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-30 13:38:21,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-30 13:38:21,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-30 13:38:21,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-30 13:38:21,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-30 13:38:21,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:21,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-30 13:38:21,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-30 13:38:21,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-30 13:38:21,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-30 13:38:21,947] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-30 13:38:21,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-30 13:38:21,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-30 13:38:21,948] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-30 13:38:21,948] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-30 13:38:21,948] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-30 13:38:21,948] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-30 13:38:21,948] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:21,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-30 13:38:21,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-30 13:38:21,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:21,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-30 13:38:21,947] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-30 13:38:21,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-30 13:38:21,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-30 13:38:21,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-30 13:38:21,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-30 13:38:21,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-30 13:38:21,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-30 13:38:21,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-30 13:38:21,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-30 13:38:21,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-30 13:38:21,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-30 13:38:21,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-30 13:38:21,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-30 13:38:21,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-30 13:38:21,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-30 13:38:21,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-30 13:38:21,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-30 13:38:21,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-30 13:38:21,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-30 13:38:21,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-30 13:38:21,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-30 13:38:21,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-30 13:38:21,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-30 13:38:21,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-30 13:38:21,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-30 13:38:21,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-30 13:38:21,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-30 13:38:21,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-30 13:38:21,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-30 13:38:21,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-30 13:38:21,960] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-30 13:38:21,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-30 13:38:21,928] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 2: [2022-11-30 13:38:21,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 9: [2022-11-30 13:38:21,928] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-30 13:38:21,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-30 13:38:21,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 2: [2022-11-30 13:38:21,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-30 13:38:21,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-30 13:38:21,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-30 13:38:21,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-30 13:38:21,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-30 13:38:21,962] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-30 13:38:21,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-30 13:38:21,962] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-30 13:38:21,962] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-30 13:38:21,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-30 13:38:21,962] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-30 13:38:21,962] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:21,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +23: [2022-11-30 13:38:21,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-30 13:38:21,964] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-30 13:38:21,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-30 13:38:21,964] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-30 13:38:21,964] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-30 13:38:21,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:21,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-30 13:38:21,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-30 13:38:21,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-30 13:38:21,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-30 13:38:21,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-30 13:38:21,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-30 13:38:21,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-30 13:38:21,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-30 13:38:21,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-30 13:38:21,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-30 13:38:21,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-30 13:38:21,967] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-30 13:38:21,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-30 13:38:21,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-30 13:38:21,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-30 13:38:21,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-30 13:38:21,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-30 13:38:21,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:21,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 9: [2022-11-30 13:38:21,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-30 13:38:21,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-30 13:38:21,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-30 13:38:21,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-30 13:38:21,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-30 13:38:21,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-30 13:38:21,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-30 13:38:21,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-30 13:38:21,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-30 13:38:21,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-30 13:38:21,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-30 13:38:21,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-30 13:38:21,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-30 13:38:21,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-30 13:38:21,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-30 13:38:21,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-30 13:38:21,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-30 13:38:21,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-30 13:38:21,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-30 13:38:21,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. + 3: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 3: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt + 3: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 3: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:21,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +19: [2022-11-30 13:38:21,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +22: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:21,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-30 13:38:21,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-30 13:38:21,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-30 13:38:21,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-30 13:38:21,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-30 13:38:21,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-30 13:38:21,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-30 13:38:21,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-30 13:38:21,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-30 13:38:21,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +26: [2022-11-30 13:38:21,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +23: [2022-11-30 13:38:21,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-30 13:38:21,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-30 13:38:21,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-30 13:38:21,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-30 13:38:21,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-30 13:38:21,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-30 13:38:21,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-30 13:38:21,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-30 13:38:21,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-30 13:38:21,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-30 13:38:21,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-30 13:38:21,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-30 13:38:21,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-30 13:38:21,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-30 13:38:21,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-30 13:38:21,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-30 13:38:21,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-30 13:38:21,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-30 13:38:21,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-30 13:38:21,983] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-30 13:38:21,983] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-30 13:38:21,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-30 13:38:21,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-30 13:38:21,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-30 13:38:21,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-30 13:38:21,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt + 6: [2022-11-30 13:38:21,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-30 13:38:21,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-30 13:38:21,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-30 13:38:21,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-30 13:38:21,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +15: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-30 13:38:21,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-30 13:38:21,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-30 13:38:21,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 0: [2022-11-30 13:38:21,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 6: [2022-11-30 13:38:21,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 0: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. + 3: [2022-11-30 13:38:21,989] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +28: [2022-11-30 13:38:21,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt + 3: [2022-11-30 13:38:21,989] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +28: [2022-11-30 13:38:21,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-30 13:38:21,989] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-30 13:38:21,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-30 13:38:21,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-30 13:38:21,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-30 13:38:21,991] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-30 13:38:21,991] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-30 13:38:21,991] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-30 13:38:21,991] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-30 13:38:21,991] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-30 13:38:21,991] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-30 13:38:21,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-30 13:38:21,994] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-30 13:38:21,994] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-30 13:38:21,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-30 13:38:21,995] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-30 13:38:21,995] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-30 13:38:21,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-30 13:38:21,995] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-30 13:38:21,995] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-30 13:38:21,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-30 13:38:21,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-30 13:38:21,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-30 13:38:21,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-30 13:38:21,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-30 13:38:21,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-30 13:38:21,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-30 13:38:21,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:21,997] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-30 13:38:21,997] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-30 13:38:21,997] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-30 13:38:21,998] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +21: [2022-11-30 13:38:21,998] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-30 13:38:21,998] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +25: [2022-11-30 13:38:21,998] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-30 13:38:21,998] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-30 13:38:21,998] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-30 13:38:21,998] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-30 13:38:21,998] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-30 13:38:21,998] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-30 13:38:21,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-30 13:38:21,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-30 13:38:21,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-30 13:38:21,999] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-30 13:38:21,999] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-30 13:38:21,999] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-30 13:38:21,999] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-30 13:38:21,999] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-30 13:38:21,999] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-30 13:38:21,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-30 13:38:21,999] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-30 13:38:21,999] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-30 13:38:22,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-30 13:38:22,001] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-30 13:38:22,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-30 13:38:22,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-30 13:38:22,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-30 13:38:22,001] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-30 13:38:22,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +14: [2022-11-30 13:38:22,001] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-30 13:38:22,001] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-30 13:38:22,001] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +12: [2022-11-30 13:38:22,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +14: [2022-11-30 13:38:22,001] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-30 13:38:22,001] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-30 13:38:22,001] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-30 13:38:22,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-30 13:38:22,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-30 13:38:22,005] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-30 13:38:22,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-30 13:38:22,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-30 13:38:22,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-30 13:38:22,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-30 13:38:22,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-30 13:38:22,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-30 13:38:22,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-30 13:38:22,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-30 13:38:22,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-30 13:38:22,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-30 13:38:22,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-30 13:38:22,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-30 13:38:22,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-30 13:38:22,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-30 13:38:22,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-30 13:38:22,010] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-30 13:38:22,010] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-30 13:38:22,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-30 13:38:22,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-30 13:38:22,011] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-30 13:38:22,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-30 13:38:22,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt + 5: [2022-11-30 13:38:22,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +26: [2022-11-30 13:38:22,011] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-30 13:38:22,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-30 13:38:22,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-30 13:38:22,011] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-30 13:38:22,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-30 13:38:22,011] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-30 13:38:22,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-30 13:38:22,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-30 13:38:22,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-30 13:38:22,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-30 13:38:22,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt + 5: [2022-11-30 13:38:22,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +30: [2022-11-30 13:38:22,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-30 13:38:22,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 5: [2022-11-30 13:38:22,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-30 13:38:22,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-30 13:38:22,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-30 13:38:22,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-30 13:38:22,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-30 13:38:22,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-30 13:38:22,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-30 13:38:22,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-30 13:38:22,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-30 13:38:22,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-30 13:38:22,003] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-30 13:38:22,003] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-30 13:38:22,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +15: [2022-11-30 13:38:22,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-30 13:38:22,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-30 13:38:22,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-30 13:38:22,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-30 13:38:22,015] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-30 13:38:22,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-30 13:38:22,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-30 13:38:22,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-30 13:38:22,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-30 13:38:22,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-30 13:38:22,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-30 13:38:22,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-30 13:38:22,019] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 6: [2022-11-30 13:38:22,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 2: [2022-11-30 13:38:22,019] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-30 13:38:22,019] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-30 13:38:22,019] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-30 13:38:22,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-30 13:38:22,020] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-30 13:38:22,020] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-30 13:38:22,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +18: [2022-11-30 13:38:22,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +10: [2022-11-30 13:38:22,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-30 13:38:22,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-30 13:38:22,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-30 13:38:22,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-30 13:38:22,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-30 13:38:22,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. + 8: [2022-11-30 13:38:22,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +30: [2022-11-30 13:38:22,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-30 13:38:22,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-30 13:38:22,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-30 13:38:22,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-30 13:38:22,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-30 13:38:22,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-30 13:38:22,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-30 13:38:22,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-30 13:38:22,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-30 13:38:22,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-30 13:38:22,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-30 13:38:22,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-30 13:38:22,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-30 13:38:22,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-30 13:38:22,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-30 13:38:22,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-30 13:38:22,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-30 13:38:22,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-30 13:38:22,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-30 13:38:22,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-30 13:38:22,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-30 13:38:22,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-30 13:38:22,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-30 13:38:22,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-30 13:38:22,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-30 13:38:22,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-30 13:38:22,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-30 13:38:22,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-30 13:38:22,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-30 13:38:22,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-30 13:38:22,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-30 13:38:22,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-30 13:38:22,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-30 13:38:22,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-30 13:38:22,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-30 13:38:22,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-30 13:38:22,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-30 13:38:22,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-30 13:38:22,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-30 13:38:22,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-30 13:38:22,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-30 13:38:22,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-30 13:38:22,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-30 13:38:22,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-30 13:38:22,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-30 13:38:22,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-30 13:38:22,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-30 13:38:22,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-30 13:38:22,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-30 13:38:22,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-30 13:38:22,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-30 13:38:22,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-30 13:38:22,053] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-30 13:38:22,053] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-30 13:38:22,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-30 13:38:22,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-30 13:38:22,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-30 13:38:22,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-30 13:38:22,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-30 13:38:22,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-30 13:38:22,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-30 13:38:22,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-30 13:38:22,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-30 13:38:22,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-30 13:38:22,066] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step20000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-30 13:38:22,066] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: successfully saved checkpoint at iteration 20000 to checkpoints_1b121b +31: time (ms) | save-checkpoint: 2917.30 +31: iteration 20010/ 39672 | consumed samples: 5122560 | consumed tokens: 10491002880 | elapsed time per iteration (s): 1.15 | learning rate: 1.102E-04 | global batch size: 256 | lm loss: 2.177945E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.359 | TFLOPs: 13.51 | +31: iteration 20020/ 39672 | consumed samples: 5125120 | consumed tokens: 10496245760 | elapsed time per iteration (s): 0.81 | learning rate: 1.101E-04 | global batch size: 256 | lm loss: 2.152947E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.445 | TFLOPs: 19.02 | +31: iteration 20030/ 39672 | consumed samples: 5127680 | consumed tokens: 10501488640 | elapsed time per iteration (s): 0.80 | learning rate: 1.100E-04 | global batch size: 256 | lm loss: 2.180871E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.471 | TFLOPs: 19.33 | +31: iteration 20040/ 39672 | consumed samples: 5130240 | consumed tokens: 10506731520 | elapsed time per iteration (s): 0.83 | learning rate: 1.100E-04 | global batch size: 256 | lm loss: 2.180751E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.309 | TFLOPs: 18.59 | +31: iteration 20050/ 39672 | consumed samples: 5132800 | consumed tokens: 10511974400 | elapsed time per iteration (s): 0.82 | learning rate: 1.099E-04 | global batch size: 256 | lm loss: 2.160203E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.619 | TFLOPs: 18.79 | +31: iteration 20060/ 39672 | consumed samples: 5135360 | consumed tokens: 10517217280 | elapsed time per iteration (s): 0.84 | learning rate: 1.098E-04 | global batch size: 256 | lm loss: 2.178703E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.559 | TFLOPs: 18.55 | +31: iteration 20070/ 39672 | consumed samples: 5137920 | consumed tokens: 10522460160 | elapsed time per iteration (s): 0.78 | learning rate: 1.097E-04 | global batch size: 256 | lm loss: 2.145447E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.523 | TFLOPs: 19.75 | +31: iteration 20080/ 39672 | consumed samples: 5140480 | consumed tokens: 10527703040 | elapsed time per iteration (s): 0.77 | learning rate: 1.097E-04 | global batch size: 256 | lm loss: 2.159621E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.062 | TFLOPs: 20.21 | +31: iteration 20090/ 39672 | consumed samples: 5143040 | consumed tokens: 10532945920 | elapsed time per iteration (s): 0.78 | learning rate: 1.096E-04 | global batch size: 256 | lm loss: 2.132574E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.125 | TFLOPs: 19.85 | +31: iteration 20100/ 39672 | consumed samples: 5145600 | consumed tokens: 10538188800 | elapsed time per iteration (s): 0.77 | learning rate: 1.095E-04 | global batch size: 256 | lm loss: 2.189387E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.814 | TFLOPs: 20.19 | +31: iteration 20110/ 39672 | consumed samples: 5148160 | consumed tokens: 10543431680 | elapsed time per iteration (s): 0.78 | learning rate: 1.095E-04 | global batch size: 256 | lm loss: 2.147533E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.291 | TFLOPs: 19.92 | +31: iteration 20120/ 39672 | consumed samples: 5150720 | consumed tokens: 10548674560 | elapsed time per iteration (s): 0.78 | learning rate: 1.094E-04 | global batch size: 256 | lm loss: 2.159354E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.459 | TFLOPs: 19.93 | +31: iteration 20130/ 39672 | consumed samples: 5153280 | consumed tokens: 10553917440 | elapsed time per iteration (s): 0.76 | learning rate: 1.093E-04 | global batch size: 256 | lm loss: 2.169960E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.851 | TFLOPs: 20.32 | +31: iteration 20140/ 39672 | consumed samples: 5155840 | consumed tokens: 10559160320 | elapsed time per iteration (s): 0.74 | learning rate: 1.092E-04 | global batch size: 256 | lm loss: 2.163123E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.234 | TFLOPs: 20.95 | +31: iteration 20150/ 39672 | consumed samples: 5158400 | consumed tokens: 10564403200 | elapsed time per iteration (s): 0.72 | learning rate: 1.092E-04 | global batch size: 256 | lm loss: 2.179728E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.619 | TFLOPs: 21.45 | +31: iteration 20160/ 39672 | consumed samples: 5160960 | consumed tokens: 10569646080 | elapsed time per iteration (s): 0.74 | learning rate: 1.091E-04 | global batch size: 256 | lm loss: 2.208257E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.857 | TFLOPs: 20.86 | +31: iteration 20170/ 39672 | consumed samples: 5163520 | consumed tokens: 10574888960 | elapsed time per iteration (s): 0.76 | learning rate: 1.090E-04 | global batch size: 256 | lm loss: 2.166968E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.756 | TFLOPs: 20.49 | +31: iteration 20180/ 39672 | consumed samples: 5166080 | consumed tokens: 10580131840 | elapsed time per iteration (s): 0.78 | learning rate: 1.090E-04 | global batch size: 256 | lm loss: 2.172845E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.920 | TFLOPs: 19.96 | +31: iteration 20190/ 39672 | consumed samples: 5168640 | consumed tokens: 10585374720 | elapsed time per iteration (s): 0.82 | learning rate: 1.089E-04 | global batch size: 256 | lm loss: 2.172716E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.911 | TFLOPs: 18.99 | +31: iteration 20200/ 39672 | consumed samples: 5171200 | consumed tokens: 10590617600 | elapsed time per iteration (s): 0.80 | learning rate: 1.088E-04 | global batch size: 256 | lm loss: 2.178785E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.457 | TFLOPs: 19.33 | +31: iteration 20210/ 39672 | consumed samples: 5173760 | consumed tokens: 10595860480 | elapsed time per iteration (s): 0.80 | learning rate: 1.087E-04 | global batch size: 256 | lm loss: 2.128945E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.181 | TFLOPs: 19.43 | +31: iteration 20220/ 39672 | consumed samples: 5176320 | consumed tokens: 10601103360 | elapsed time per iteration (s): 0.84 | learning rate: 1.087E-04 | global batch size: 256 | lm loss: 2.150889E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.456 | TFLOPs: 18.36 | +31: iteration 20230/ 39672 | consumed samples: 5178880 | consumed tokens: 10606346240 | elapsed time per iteration (s): 0.81 | learning rate: 1.086E-04 | global batch size: 256 | lm loss: 2.168700E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.508 | TFLOPs: 19.15 | +31: iteration 20240/ 39672 | consumed samples: 5181440 | consumed tokens: 10611589120 | elapsed time per iteration (s): 0.77 | learning rate: 1.085E-04 | global batch size: 256 | lm loss: 2.166194E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.432 | TFLOPs: 20.23 | +31: iteration 20250/ 39672 | consumed samples: 5184000 | consumed tokens: 10616832000 | elapsed time per iteration (s): 0.77 | learning rate: 1.085E-04 | global batch size: 256 | lm loss: 2.156464E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.810 | TFLOPs: 20.01 | +31: iteration 20260/ 39672 | consumed samples: 5186560 | consumed tokens: 10622074880 | elapsed time per iteration (s): 0.76 | learning rate: 1.084E-04 | global batch size: 256 | lm loss: 2.161540E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.943 | TFLOPs: 20.51 | +31: iteration 20270/ 39672 | consumed samples: 5189120 | consumed tokens: 10627317760 | elapsed time per iteration (s): 0.75 | learning rate: 1.083E-04 | global batch size: 256 | lm loss: 2.164960E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.989 | TFLOPs: 20.75 | +31: iteration 20280/ 39672 | consumed samples: 5191680 | consumed tokens: 10632560640 | elapsed time per iteration (s): 0.79 | learning rate: 1.082E-04 | global batch size: 256 | lm loss: 2.173857E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.824 | TFLOPs: 19.59 | +31: iteration 20290/ 39672 | consumed samples: 5194240 | consumed tokens: 10637803520 | elapsed time per iteration (s): 0.72 | learning rate: 1.082E-04 | global batch size: 256 | lm loss: 2.203784E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.433 | TFLOPs: 21.50 | +31: iteration 20300/ 39672 | consumed samples: 5196800 | consumed tokens: 10643046400 | elapsed time per iteration (s): 0.81 | learning rate: 1.081E-04 | global batch size: 256 | lm loss: 2.154613E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.118 | TFLOPs: 19.06 | +31: iteration 20310/ 39672 | consumed samples: 5199360 | consumed tokens: 10648289280 | elapsed time per iteration (s): 0.75 | learning rate: 1.080E-04 | global batch size: 256 | lm loss: 2.155471E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.275 | TFLOPs: 20.59 | +31: iteration 20320/ 39672 | consumed samples: 5201920 | consumed tokens: 10653532160 | elapsed time per iteration (s): 0.81 | learning rate: 1.079E-04 | global batch size: 256 | lm loss: 2.170445E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.397 | TFLOPs: 19.20 | +31: iteration 20330/ 39672 | consumed samples: 5204480 | consumed tokens: 10658775040 | elapsed time per iteration (s): 0.80 | learning rate: 1.079E-04 | global batch size: 256 | lm loss: 2.188169E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.241 | TFLOPs: 19.43 | +31: iteration 20340/ 39672 | consumed samples: 5207040 | consumed tokens: 10664017920 | elapsed time per iteration (s): 0.81 | learning rate: 1.078E-04 | global batch size: 256 | lm loss: 2.159531E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.050 | TFLOPs: 19.12 | +31: iteration 20350/ 39672 | consumed samples: 5209600 | consumed tokens: 10669260800 | elapsed time per iteration (s): 0.78 | learning rate: 1.077E-04 | global batch size: 256 | lm loss: 2.131781E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.941 | TFLOPs: 19.78 | +31: iteration 20360/ 39672 | consumed samples: 5212160 | consumed tokens: 10674503680 | elapsed time per iteration (s): 0.76 | learning rate: 1.077E-04 | global batch size: 256 | lm loss: 2.173508E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.550 | TFLOPs: 20.42 | +31: iteration 20370/ 39672 | consumed samples: 5214720 | consumed tokens: 10679746560 | elapsed time per iteration (s): 0.80 | learning rate: 1.076E-04 | global batch size: 256 | lm loss: 2.148293E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.297 | TFLOPs: 19.38 | +31: iteration 20380/ 39672 | consumed samples: 5217280 | consumed tokens: 10684989440 | elapsed time per iteration (s): 0.82 | learning rate: 1.075E-04 | global batch size: 256 | lm loss: 2.172671E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.572 | TFLOPs: 18.85 | +31: iteration 20390/ 39672 | consumed samples: 5219840 | consumed tokens: 10690232320 | elapsed time per iteration (s): 0.88 | learning rate: 1.074E-04 | global batch size: 256 | lm loss: 2.144691E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 292.237 | TFLOPs: 17.68 | +31: iteration 20400/ 39672 | consumed samples: 5222400 | consumed tokens: 10695475200 | elapsed time per iteration (s): 0.82 | learning rate: 1.074E-04 | global batch size: 256 | lm loss: 2.194005E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.120 | TFLOPs: 18.88 | +31: iteration 20410/ 39672 | consumed samples: 5224960 | consumed tokens: 10700718080 | elapsed time per iteration (s): 0.80 | learning rate: 1.073E-04 | global batch size: 256 | lm loss: 2.150839E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.227 | TFLOPs: 19.31 | +31: iteration 20420/ 39672 | consumed samples: 5227520 | consumed tokens: 10705960960 | elapsed time per iteration (s): 0.84 | learning rate: 1.072E-04 | global batch size: 256 | lm loss: 2.183826E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.118 | TFLOPs: 18.52 | +31: iteration 20430/ 39672 | consumed samples: 5230080 | consumed tokens: 10711203840 | elapsed time per iteration (s): 0.82 | learning rate: 1.072E-04 | global batch size: 256 | lm loss: 2.176005E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.906 | TFLOPs: 18.99 | +31: iteration 20440/ 39672 | consumed samples: 5232640 | consumed tokens: 10716446720 | elapsed time per iteration (s): 0.83 | learning rate: 1.071E-04 | global batch size: 256 | lm loss: 2.175710E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.970 | TFLOPs: 18.63 | +31: iteration 20450/ 39672 | consumed samples: 5235200 | consumed tokens: 10721689600 | elapsed time per iteration (s): 0.84 | learning rate: 1.070E-04 | global batch size: 256 | lm loss: 2.163818E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.082 | TFLOPs: 18.34 | +31: iteration 20460/ 39672 | consumed samples: 5237760 | consumed tokens: 10726932480 | elapsed time per iteration (s): 0.82 | learning rate: 1.069E-04 | global batch size: 256 | lm loss: 2.163453E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.609 | TFLOPs: 18.79 | +31: iteration 20470/ 39672 | consumed samples: 5240320 | consumed tokens: 10732175360 | elapsed time per iteration (s): 0.82 | learning rate: 1.069E-04 | global batch size: 256 | lm loss: 2.163451E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.565 | TFLOPs: 18.79 | +31: iteration 20480/ 39672 | consumed samples: 5242880 | consumed tokens: 10737418240 | elapsed time per iteration (s): 0.78 | learning rate: 1.068E-04 | global batch size: 256 | lm loss: 2.173437E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.749 | TFLOPs: 19.77 | +31: iteration 20490/ 39672 | consumed samples: 5245440 | consumed tokens: 10742661120 | elapsed time per iteration (s): 0.82 | learning rate: 1.067E-04 | global batch size: 256 | lm loss: 2.167066E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.529 | TFLOPs: 18.85 | +31: iteration 20500/ 39672 | consumed samples: 5248000 | consumed tokens: 10747904000 | elapsed time per iteration (s): 0.75 | learning rate: 1.067E-04 | global batch size: 256 | lm loss: 2.176243E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.061 | TFLOPs: 20.57 | +31: iteration 20510/ 39672 | consumed samples: 5250560 | consumed tokens: 10753146880 | elapsed time per iteration (s): 0.79 | learning rate: 1.066E-04 | global batch size: 256 | lm loss: 2.167558E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.149 | TFLOPs: 19.67 | +31: iteration 20520/ 39672 | consumed samples: 5253120 | consumed tokens: 10758389760 | elapsed time per iteration (s): 0.78 | learning rate: 1.065E-04 | global batch size: 256 | lm loss: 2.214499E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.603 | TFLOPs: 19.94 | +31: iteration 20530/ 39672 | consumed samples: 5255680 | consumed tokens: 10763632640 | elapsed time per iteration (s): 0.83 | learning rate: 1.064E-04 | global batch size: 256 | lm loss: 2.179064E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.374 | TFLOPs: 18.60 | +31: iteration 20540/ 39672 | consumed samples: 5258240 | consumed tokens: 10768875520 | elapsed time per iteration (s): 0.77 | learning rate: 1.064E-04 | global batch size: 256 | lm loss: 2.151136E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.784 | TFLOPs: 20.13 | +31: iteration 20550/ 39672 | consumed samples: 5260800 | consumed tokens: 10774118400 | elapsed time per iteration (s): 0.79 | learning rate: 1.063E-04 | global batch size: 256 | lm loss: 2.182287E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.746 | TFLOPs: 19.59 | +31: iteration 20560/ 39672 | consumed samples: 5263360 | consumed tokens: 10779361280 | elapsed time per iteration (s): 0.75 | learning rate: 1.062E-04 | global batch size: 256 | lm loss: 2.167966E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.772 | TFLOPs: 20.68 | +31: iteration 20570/ 39672 | consumed samples: 5265920 | consumed tokens: 10784604160 | elapsed time per iteration (s): 0.77 | learning rate: 1.061E-04 | global batch size: 256 | lm loss: 2.158083E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.968 | TFLOPs: 20.08 | +31: iteration 20580/ 39672 | consumed samples: 5268480 | consumed tokens: 10789847040 | elapsed time per iteration (s): 0.77 | learning rate: 1.061E-04 | global batch size: 256 | lm loss: 2.139919E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.976 | TFLOPs: 20.14 | +31: iteration 20590/ 39672 | consumed samples: 5271040 | consumed tokens: 10795089920 | elapsed time per iteration (s): 0.79 | learning rate: 1.060E-04 | global batch size: 256 | lm loss: 2.169686E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.529 | TFLOPs: 19.57 | +31: iteration 20600/ 39672 | consumed samples: 5273600 | consumed tokens: 10800332800 | elapsed time per iteration (s): 0.85 | learning rate: 1.059E-04 | global batch size: 256 | lm loss: 2.148765E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.161 | TFLOPs: 18.16 | +31: iteration 20610/ 39672 | consumed samples: 5276160 | consumed tokens: 10805575680 | elapsed time per iteration (s): 0.85 | learning rate: 1.059E-04 | global batch size: 256 | lm loss: 2.154219E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.329 | TFLOPs: 18.29 | +31: iteration 20620/ 39672 | consumed samples: 5278720 | consumed tokens: 10810818560 | elapsed time per iteration (s): 0.83 | learning rate: 1.058E-04 | global batch size: 256 | lm loss: 2.143681E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.451 | TFLOPs: 18.66 | +31: iteration 20630/ 39672 | consumed samples: 5281280 | consumed tokens: 10816061440 | elapsed time per iteration (s): 0.83 | learning rate: 1.057E-04 | global batch size: 256 | lm loss: 2.194244E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.487 | TFLOPs: 18.72 | +31: iteration 20640/ 39672 | consumed samples: 5283840 | consumed tokens: 10821304320 | elapsed time per iteration (s): 0.84 | learning rate: 1.056E-04 | global batch size: 256 | lm loss: 2.171889E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.954 | TFLOPs: 18.39 | +31: iteration 20650/ 39672 | consumed samples: 5286400 | consumed tokens: 10826547200 | elapsed time per iteration (s): 0.83 | learning rate: 1.056E-04 | global batch size: 256 | lm loss: 2.166482E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.782 | TFLOPs: 18.74 | +31: iteration 20660/ 39672 | consumed samples: 5288960 | consumed tokens: 10831790080 | elapsed time per iteration (s): 0.85 | learning rate: 1.055E-04 | global batch size: 256 | lm loss: 2.191138E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.066 | TFLOPs: 18.15 | +31: iteration 20670/ 39672 | consumed samples: 5291520 | consumed tokens: 10837032960 | elapsed time per iteration (s): 0.83 | learning rate: 1.054E-04 | global batch size: 256 | lm loss: 2.167505E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.083 | TFLOPs: 18.70 | +31: iteration 20680/ 39672 | consumed samples: 5294080 | consumed tokens: 10842275840 | elapsed time per iteration (s): 0.85 | learning rate: 1.054E-04 | global batch size: 256 | lm loss: 2.152215E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.211 | TFLOPs: 18.22 | +31: iteration 20690/ 39672 | consumed samples: 5296640 | consumed tokens: 10847518720 | elapsed time per iteration (s): 0.85 | learning rate: 1.053E-04 | global batch size: 256 | lm loss: 2.161766E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.385 | TFLOPs: 18.23 | +31: iteration 20700/ 39672 | consumed samples: 5299200 | consumed tokens: 10852761600 | elapsed time per iteration (s): 0.81 | learning rate: 1.052E-04 | global batch size: 256 | lm loss: 2.172631E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.966 | TFLOPs: 19.18 | +31: iteration 20710/ 39672 | consumed samples: 5301760 | consumed tokens: 10858004480 | elapsed time per iteration (s): 0.84 | learning rate: 1.051E-04 | global batch size: 256 | lm loss: 2.146469E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.831 | TFLOPs: 18.44 | +31: iteration 20720/ 39672 | consumed samples: 5304320 | consumed tokens: 10863247360 | elapsed time per iteration (s): 0.82 | learning rate: 1.051E-04 | global batch size: 256 | lm loss: 2.153247E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.949 | TFLOPs: 18.87 | +31: iteration 20730/ 39672 | consumed samples: 5306880 | consumed tokens: 10868490240 | elapsed time per iteration (s): 0.83 | learning rate: 1.050E-04 | global batch size: 256 | lm loss: 2.166175E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.824 | TFLOPs: 18.56 | +31: iteration 20740/ 39672 | consumed samples: 5309440 | consumed tokens: 10873733120 | elapsed time per iteration (s): 0.84 | learning rate: 1.049E-04 | global batch size: 256 | lm loss: 2.153022E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.784 | TFLOPs: 18.38 | +31: iteration 20750/ 39672 | consumed samples: 5312000 | consumed tokens: 10878976000 | elapsed time per iteration (s): 0.83 | learning rate: 1.049E-04 | global batch size: 256 | lm loss: 2.166995E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.060 | TFLOPs: 18.64 | +31: iteration 20760/ 39672 | consumed samples: 5314560 | consumed tokens: 10884218880 | elapsed time per iteration (s): 0.88 | learning rate: 1.048E-04 | global batch size: 256 | lm loss: 2.172708E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 291.584 | TFLOPs: 17.64 | +31: iteration 20770/ 39672 | consumed samples: 5317120 | consumed tokens: 10889461760 | elapsed time per iteration (s): 0.78 | learning rate: 1.047E-04 | global batch size: 256 | lm loss: 2.164971E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.193 | TFLOPs: 19.85 | +31: iteration 20780/ 39672 | consumed samples: 5319680 | consumed tokens: 10894704640 | elapsed time per iteration (s): 0.83 | learning rate: 1.046E-04 | global batch size: 256 | lm loss: 2.164271E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.200 | TFLOPs: 18.77 | +31: iteration 20790/ 39672 | consumed samples: 5322240 | consumed tokens: 10899947520 | elapsed time per iteration (s): 0.83 | learning rate: 1.046E-04 | global batch size: 256 | lm loss: 2.167736E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.142 | TFLOPs: 18.76 | +31: iteration 20800/ 39672 | consumed samples: 5324800 | consumed tokens: 10905190400 | elapsed time per iteration (s): 0.86 | learning rate: 1.045E-04 | global batch size: 256 | lm loss: 2.191281E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.216 | TFLOPs: 18.04 | +31: iteration 20810/ 39672 | consumed samples: 5327360 | consumed tokens: 10910433280 | elapsed time per iteration (s): 0.86 | learning rate: 1.044E-04 | global batch size: 256 | lm loss: 2.164594E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.060 | TFLOPs: 18.03 | +31: iteration 20820/ 39672 | consumed samples: 5329920 | consumed tokens: 10915676160 | elapsed time per iteration (s): 0.92 | learning rate: 1.044E-04 | global batch size: 256 | lm loss: 2.166360E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 278.140 | TFLOPs: 16.83 | +31: iteration 20830/ 39672 | consumed samples: 5332480 | consumed tokens: 10920919040 | elapsed time per iteration (s): 0.83 | learning rate: 1.043E-04 | global batch size: 256 | lm loss: 2.133891E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.245 | TFLOPs: 18.77 | +31: iteration 20840/ 39672 | consumed samples: 5335040 | consumed tokens: 10926161920 | elapsed time per iteration (s): 0.81 | learning rate: 1.042E-04 | global batch size: 256 | lm loss: 2.155070E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.927 | TFLOPs: 19.11 | +31: iteration 20850/ 39672 | consumed samples: 5337600 | consumed tokens: 10931404800 | elapsed time per iteration (s): 0.83 | learning rate: 1.041E-04 | global batch size: 256 | lm loss: 2.167399E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.153 | TFLOPs: 18.76 | +31: iteration 20860/ 39672 | consumed samples: 5340160 | consumed tokens: 10936647680 | elapsed time per iteration (s): 0.85 | learning rate: 1.041E-04 | global batch size: 256 | lm loss: 2.169189E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.941 | TFLOPs: 18.33 | +31: iteration 20870/ 39672 | consumed samples: 5342720 | consumed tokens: 10941890560 | elapsed time per iteration (s): 0.86 | learning rate: 1.040E-04 | global batch size: 256 | lm loss: 2.182017E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.964 | TFLOPs: 18.03 | +31: iteration 20880/ 39672 | consumed samples: 5345280 | consumed tokens: 10947133440 | elapsed time per iteration (s): 0.86 | learning rate: 1.039E-04 | global batch size: 256 | lm loss: 2.168704E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.985 | TFLOPs: 17.97 | +31: iteration 20890/ 39672 | consumed samples: 5347840 | consumed tokens: 10952376320 | elapsed time per iteration (s): 0.83 | learning rate: 1.038E-04 | global batch size: 256 | lm loss: 2.152536E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.848 | TFLOPs: 18.75 | +31: iteration 20900/ 39672 | consumed samples: 5350400 | consumed tokens: 10957619200 | elapsed time per iteration (s): 0.82 | learning rate: 1.038E-04 | global batch size: 256 | lm loss: 2.154732E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.067 | TFLOPs: 19.00 | +31: iteration 20910/ 39672 | consumed samples: 5352960 | consumed tokens: 10962862080 | elapsed time per iteration (s): 0.84 | learning rate: 1.037E-04 | global batch size: 256 | lm loss: 2.152594E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.315 | TFLOPs: 18.35 | +31: iteration 20920/ 39672 | consumed samples: 5355520 | consumed tokens: 10968104960 | elapsed time per iteration (s): 0.88 | learning rate: 1.036E-04 | global batch size: 256 | lm loss: 2.157390E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 289.599 | TFLOPs: 17.52 | +31: iteration 20930/ 39672 | consumed samples: 5358080 | consumed tokens: 10973347840 | elapsed time per iteration (s): 0.79 | learning rate: 1.036E-04 | global batch size: 256 | lm loss: 2.161926E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.007 | TFLOPs: 19.60 | +31: iteration 20940/ 39672 | consumed samples: 5360640 | consumed tokens: 10978590720 | elapsed time per iteration (s): 0.81 | learning rate: 1.035E-04 | global batch size: 256 | lm loss: 2.137479E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.901 | TFLOPs: 19.11 | +31: iteration 20950/ 39672 | consumed samples: 5363200 | consumed tokens: 10983833600 | elapsed time per iteration (s): 0.83 | learning rate: 1.034E-04 | global batch size: 256 | lm loss: 2.150987E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.877 | TFLOPs: 18.69 | +31: iteration 20960/ 39672 | consumed samples: 5365760 | consumed tokens: 10989076480 | elapsed time per iteration (s): 0.86 | learning rate: 1.033E-04 | global batch size: 256 | lm loss: 2.156607E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.697 | TFLOPs: 18.01 | +31: iteration 20970/ 39672 | consumed samples: 5368320 | consumed tokens: 10994319360 | elapsed time per iteration (s): 0.83 | learning rate: 1.033E-04 | global batch size: 256 | lm loss: 2.150215E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.291 | TFLOPs: 18.77 | +31: iteration 20980/ 39672 | consumed samples: 5370880 | consumed tokens: 10999562240 | elapsed time per iteration (s): 0.84 | learning rate: 1.032E-04 | global batch size: 256 | lm loss: 2.138417E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.722 | TFLOPs: 18.43 | +31: iteration 20990/ 39672 | consumed samples: 5373440 | consumed tokens: 11004805120 | elapsed time per iteration (s): 0.83 | learning rate: 1.031E-04 | global batch size: 256 | lm loss: 2.164903E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.840 | TFLOPs: 18.62 | +31: iteration 21000/ 39672 | consumed samples: 5376000 | consumed tokens: 11010048000 | elapsed time per iteration (s): 0.81 | learning rate: 1.031E-04 | global batch size: 256 | lm loss: 2.170679E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.494 | TFLOPs: 19.15 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 21000 | lm loss value: 2.136333E+00 | lm loss PPL: 8.468323E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 21010/ 39672 | consumed samples: 5378560 | consumed tokens: 11015290880 | elapsed time per iteration (s): 0.84 | learning rate: 1.030E-04 | global batch size: 256 | lm loss: 2.180113E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.711 | TFLOPs: 18.49 | +31: iteration 21020/ 39672 | consumed samples: 5381120 | consumed tokens: 11020533760 | elapsed time per iteration (s): 1.08 | learning rate: 1.029E-04 | global batch size: 256 | lm loss: 2.174156E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 237.904 | TFLOPs: 14.39 | +31: iteration 21030/ 39672 | consumed samples: 5383680 | consumed tokens: 11025776640 | elapsed time per iteration (s): 0.83 | learning rate: 1.028E-04 | global batch size: 256 | lm loss: 2.188806E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.051 | TFLOPs: 18.64 | +31: iteration 21040/ 39672 | consumed samples: 5386240 | consumed tokens: 11031019520 | elapsed time per iteration (s): 0.80 | learning rate: 1.028E-04 | global batch size: 256 | lm loss: 2.147827E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.587 | TFLOPs: 19.46 | +31: iteration 21050/ 39672 | consumed samples: 5388800 | consumed tokens: 11036262400 | elapsed time per iteration (s): 0.84 | learning rate: 1.027E-04 | global batch size: 256 | lm loss: 2.164537E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.962 | TFLOPs: 18.45 | +31: iteration 21060/ 39672 | consumed samples: 5391360 | consumed tokens: 11041505280 | elapsed time per iteration (s): 0.84 | learning rate: 1.026E-04 | global batch size: 256 | lm loss: 2.191583E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.392 | TFLOPs: 18.41 | +31: iteration 21070/ 39672 | consumed samples: 5393920 | consumed tokens: 11046748160 | elapsed time per iteration (s): 0.83 | learning rate: 1.026E-04 | global batch size: 256 | lm loss: 2.145213E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.099 | TFLOPs: 18.70 | +31: iteration 21080/ 39672 | consumed samples: 5396480 | consumed tokens: 11051991040 | elapsed time per iteration (s): 0.80 | learning rate: 1.025E-04 | global batch size: 256 | lm loss: 2.142538E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.714 | TFLOPs: 19.28 | +31: iteration 21090/ 39672 | consumed samples: 5399040 | consumed tokens: 11057233920 | elapsed time per iteration (s): 0.86 | learning rate: 1.024E-04 | global batch size: 256 | lm loss: 2.145005E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.737 | TFLOPs: 18.01 | +31: iteration 21100/ 39672 | consumed samples: 5401600 | consumed tokens: 11062476800 | elapsed time per iteration (s): 0.82 | learning rate: 1.023E-04 | global batch size: 256 | lm loss: 2.148962E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.889 | TFLOPs: 18.99 | +31: iteration 21110/ 39672 | consumed samples: 5404160 | consumed tokens: 11067719680 | elapsed time per iteration (s): 0.80 | learning rate: 1.023E-04 | global batch size: 256 | lm loss: 2.184338E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.815 | TFLOPs: 19.29 | +31: iteration 21120/ 39672 | consumed samples: 5406720 | consumed tokens: 11072962560 | elapsed time per iteration (s): 0.81 | learning rate: 1.022E-04 | global batch size: 256 | lm loss: 2.182866E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.389 | TFLOPs: 19.08 | +31: iteration 21130/ 39672 | consumed samples: 5409280 | consumed tokens: 11078205440 | elapsed time per iteration (s): 0.80 | learning rate: 1.021E-04 | global batch size: 256 | lm loss: 2.146161E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.447 | TFLOPs: 19.33 | +31: iteration 21140/ 39672 | consumed samples: 5411840 | consumed tokens: 11083448320 | elapsed time per iteration (s): 0.87 | learning rate: 1.021E-04 | global batch size: 256 | lm loss: 2.163326E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.208 | TFLOPs: 17.86 | +31: iteration 21150/ 39672 | consumed samples: 5414400 | consumed tokens: 11088691200 | elapsed time per iteration (s): 0.80 | learning rate: 1.020E-04 | global batch size: 256 | lm loss: 2.179284E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.134 | TFLOPs: 19.31 | +31: iteration 21160/ 39672 | consumed samples: 5416960 | consumed tokens: 11093934080 | elapsed time per iteration (s): 0.83 | learning rate: 1.019E-04 | global batch size: 256 | lm loss: 2.167222E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.657 | TFLOPs: 18.61 | +31: iteration 21170/ 39672 | consumed samples: 5419520 | consumed tokens: 11099176960 | elapsed time per iteration (s): 0.79 | learning rate: 1.018E-04 | global batch size: 256 | lm loss: 2.147431E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.045 | TFLOPs: 19.66 | +31: iteration 21180/ 39672 | consumed samples: 5422080 | consumed tokens: 11104419840 | elapsed time per iteration (s): 0.81 | learning rate: 1.018E-04 | global batch size: 256 | lm loss: 2.147282E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.674 | TFLOPs: 19.22 | +31: iteration 21190/ 39672 | consumed samples: 5424640 | consumed tokens: 11109662720 | elapsed time per iteration (s): 0.81 | learning rate: 1.017E-04 | global batch size: 256 | lm loss: 2.163808E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.490 | TFLOPs: 19.09 | +31: iteration 21200/ 39672 | consumed samples: 5427200 | consumed tokens: 11114905600 | elapsed time per iteration (s): 0.81 | learning rate: 1.016E-04 | global batch size: 256 | lm loss: 2.150517E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.709 | TFLOPs: 19.04 | +31: iteration 21210/ 39672 | consumed samples: 5429760 | consumed tokens: 11120148480 | elapsed time per iteration (s): 0.81 | learning rate: 1.016E-04 | global batch size: 256 | lm loss: 2.142816E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.204 | TFLOPs: 19.19 | +31: iteration 21220/ 39672 | consumed samples: 5432320 | consumed tokens: 11125391360 | elapsed time per iteration (s): 0.87 | learning rate: 1.015E-04 | global batch size: 256 | lm loss: 2.157745E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 292.793 | TFLOPs: 17.71 | +31: iteration 21230/ 39672 | consumed samples: 5434880 | consumed tokens: 11130634240 | elapsed time per iteration (s): 0.80 | learning rate: 1.014E-04 | global batch size: 256 | lm loss: 2.138744E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.749 | TFLOPs: 19.46 | +31: iteration 21240/ 39672 | consumed samples: 5437440 | consumed tokens: 11135877120 | elapsed time per iteration (s): 0.82 | learning rate: 1.013E-04 | global batch size: 256 | lm loss: 2.127924E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.011 | TFLOPs: 18.88 | +31: iteration 21250/ 39672 | consumed samples: 5440000 | consumed tokens: 11141120000 | elapsed time per iteration (s): 0.82 | learning rate: 1.013E-04 | global batch size: 256 | lm loss: 2.190383E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.329 | TFLOPs: 18.96 | +31: iteration 21260/ 39672 | consumed samples: 5442560 | consumed tokens: 11146362880 | elapsed time per iteration (s): 0.80 | learning rate: 1.012E-04 | global batch size: 256 | lm loss: 2.166354E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.472 | TFLOPs: 19.27 | +31: iteration 21270/ 39672 | consumed samples: 5445120 | consumed tokens: 11151605760 | elapsed time per iteration (s): 0.79 | learning rate: 1.011E-04 | global batch size: 256 | lm loss: 2.144123E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.930 | TFLOPs: 19.72 | +31: iteration 21280/ 39672 | consumed samples: 5447680 | consumed tokens: 11156848640 | elapsed time per iteration (s): 0.82 | learning rate: 1.011E-04 | global batch size: 256 | lm loss: 2.157838E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.308 | TFLOPs: 18.83 | +31: iteration 21290/ 39672 | consumed samples: 5450240 | consumed tokens: 11162091520 | elapsed time per iteration (s): 0.82 | learning rate: 1.010E-04 | global batch size: 256 | lm loss: 2.200157E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.409 | TFLOPs: 18.90 | +31: iteration 21300/ 39672 | consumed samples: 5452800 | consumed tokens: 11167334400 | elapsed time per iteration (s): 1.06 | learning rate: 1.009E-04 | global batch size: 256 | lm loss: 2.154924E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 240.490 | TFLOPs: 14.55 | +31: iteration 21310/ 39672 | consumed samples: 5455360 | consumed tokens: 11172577280 | elapsed time per iteration (s): 0.85 | learning rate: 1.008E-04 | global batch size: 256 | lm loss: 2.148454E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.941 | TFLOPs: 18.27 | +31: iteration 21320/ 39672 | consumed samples: 5457920 | consumed tokens: 11177820160 | elapsed time per iteration (s): 0.84 | learning rate: 1.008E-04 | global batch size: 256 | lm loss: 2.164357E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.167 | TFLOPs: 18.34 | +31: iteration 21330/ 39672 | consumed samples: 5460480 | consumed tokens: 11183063040 | elapsed time per iteration (s): 0.82 | learning rate: 1.007E-04 | global batch size: 256 | lm loss: 2.144860E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.253 | TFLOPs: 18.95 | +31: iteration 21340/ 39672 | consumed samples: 5463040 | consumed tokens: 11188305920 | elapsed time per iteration (s): 0.89 | learning rate: 1.006E-04 | global batch size: 256 | lm loss: 2.152410E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 287.023 | TFLOPs: 17.36 | +31: iteration 21350/ 39672 | consumed samples: 5465600 | consumed tokens: 11193548800 | elapsed time per iteration (s): 0.84 | learning rate: 1.005E-04 | global batch size: 256 | lm loss: 2.178282E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.183 | TFLOPs: 18.46 | +31: iteration 21360/ 39672 | consumed samples: 5468160 | consumed tokens: 11198791680 | elapsed time per iteration (s): 0.84 | learning rate: 1.005E-04 | global batch size: 256 | lm loss: 2.177741E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.797 | TFLOPs: 18.38 | +31: iteration 21370/ 39672 | consumed samples: 5470720 | consumed tokens: 11204034560 | elapsed time per iteration (s): 0.79 | learning rate: 1.004E-04 | global batch size: 256 | lm loss: 2.181130E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.027 | TFLOPs: 19.66 | +31: iteration 21380/ 39672 | consumed samples: 5473280 | consumed tokens: 11209277440 | elapsed time per iteration (s): 0.85 | learning rate: 1.003E-04 | global batch size: 256 | lm loss: 2.130531E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.897 | TFLOPs: 18.14 | +31: iteration 21390/ 39672 | consumed samples: 5475840 | consumed tokens: 11214520320 | elapsed time per iteration (s): 0.84 | learning rate: 1.003E-04 | global batch size: 256 | lm loss: 2.164119E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.685 | TFLOPs: 18.49 | +31: iteration 21400/ 39672 | consumed samples: 5478400 | consumed tokens: 11219763200 | elapsed time per iteration (s): 0.79 | learning rate: 1.002E-04 | global batch size: 256 | lm loss: 2.158484E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.490 | TFLOPs: 19.63 | +31: iteration 21410/ 39672 | consumed samples: 5480960 | consumed tokens: 11225006080 | elapsed time per iteration (s): 0.79 | learning rate: 1.001E-04 | global batch size: 256 | lm loss: 2.181445E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.037 | TFLOPs: 19.72 | +31: iteration 21420/ 39672 | consumed samples: 5483520 | consumed tokens: 11230248960 | elapsed time per iteration (s): 0.79 | learning rate: 1.000E-04 | global batch size: 256 | lm loss: 2.159165E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.538 | TFLOPs: 19.51 | +31: iteration 21430/ 39672 | consumed samples: 5486080 | consumed tokens: 11235491840 | elapsed time per iteration (s): 0.80 | learning rate: 9.998E-05 | global batch size: 256 | lm loss: 2.190543E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.244 | TFLOPs: 19.25 | +31: iteration 21440/ 39672 | consumed samples: 5488640 | consumed tokens: 11240734720 | elapsed time per iteration (s): 0.82 | learning rate: 9.991E-05 | global batch size: 256 | lm loss: 2.178989E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.438 | TFLOPs: 18.84 | +31: iteration 21450/ 39672 | consumed samples: 5491200 | consumed tokens: 11245977600 | elapsed time per iteration (s): 0.82 | learning rate: 9.983E-05 | global batch size: 256 | lm loss: 2.174436E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.556 | TFLOPs: 18.91 | +31: iteration 21460/ 39672 | consumed samples: 5493760 | consumed tokens: 11251220480 | elapsed time per iteration (s): 0.80 | learning rate: 9.976E-05 | global batch size: 256 | lm loss: 2.154566E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.787 | TFLOPs: 19.41 | +31: iteration 21470/ 39672 | consumed samples: 5496320 | consumed tokens: 11256463360 | elapsed time per iteration (s): 0.81 | learning rate: 9.969E-05 | global batch size: 256 | lm loss: 2.152967E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.586 | TFLOPs: 19.15 | +31: iteration 21480/ 39672 | consumed samples: 5498880 | consumed tokens: 11261706240 | elapsed time per iteration (s): 0.83 | learning rate: 9.962E-05 | global batch size: 256 | lm loss: 2.157116E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.887 | TFLOPs: 18.63 | +31: iteration 21490/ 39672 | consumed samples: 5501440 | consumed tokens: 11266949120 | elapsed time per iteration (s): 0.82 | learning rate: 9.955E-05 | global batch size: 256 | lm loss: 2.184845E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.738 | TFLOPs: 18.86 | +31: iteration 21500/ 39672 | consumed samples: 5504000 | consumed tokens: 11272192000 | elapsed time per iteration (s): 0.88 | learning rate: 9.948E-05 | global batch size: 256 | lm loss: 2.163385E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 291.394 | TFLOPs: 17.63 | +31: iteration 21510/ 39672 | consumed samples: 5506560 | consumed tokens: 11277434880 | elapsed time per iteration (s): 0.81 | learning rate: 9.940E-05 | global batch size: 256 | lm loss: 2.129413E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.502 | TFLOPs: 19.09 | +31: iteration 21520/ 39672 | consumed samples: 5509120 | consumed tokens: 11282677760 | elapsed time per iteration (s): 0.84 | learning rate: 9.933E-05 | global batch size: 256 | lm loss: 2.169538E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.466 | TFLOPs: 18.54 | +31: iteration 21530/ 39672 | consumed samples: 5511680 | consumed tokens: 11287920640 | elapsed time per iteration (s): 0.80 | learning rate: 9.926E-05 | global batch size: 256 | lm loss: 2.134498E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.824 | TFLOPs: 19.47 | +31: iteration 21540/ 39672 | consumed samples: 5514240 | consumed tokens: 11293163520 | elapsed time per iteration (s): 0.82 | learning rate: 9.919E-05 | global batch size: 256 | lm loss: 2.121189E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.569 | TFLOPs: 18.85 | +31: iteration 21550/ 39672 | consumed samples: 5516800 | consumed tokens: 11298406400 | elapsed time per iteration (s): 0.81 | learning rate: 9.912E-05 | global batch size: 256 | lm loss: 2.171708E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.074 | TFLOPs: 19.06 | +31: iteration 21560/ 39672 | consumed samples: 5519360 | consumed tokens: 11303649280 | elapsed time per iteration (s): 0.78 | learning rate: 9.905E-05 | global batch size: 256 | lm loss: 2.146749E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.567 | TFLOPs: 19.82 | +31: iteration 21570/ 39672 | consumed samples: 5521920 | consumed tokens: 11308892160 | elapsed time per iteration (s): 0.79 | learning rate: 9.898E-05 | global batch size: 256 | lm loss: 2.147004E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.058 | TFLOPs: 19.54 | +31: iteration 21580/ 39672 | consumed samples: 5524480 | consumed tokens: 11314135040 | elapsed time per iteration (s): 0.78 | learning rate: 9.890E-05 | global batch size: 256 | lm loss: 2.158784E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.240 | TFLOPs: 19.74 | +31: iteration 21590/ 39672 | consumed samples: 5527040 | consumed tokens: 11319377920 | elapsed time per iteration (s): 0.73 | learning rate: 9.883E-05 | global batch size: 256 | lm loss: 2.124530E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.194 | TFLOPs: 21.13 | +31: iteration 21600/ 39672 | consumed samples: 5529600 | consumed tokens: 11324620800 | elapsed time per iteration (s): 0.76 | learning rate: 9.876E-05 | global batch size: 256 | lm loss: 2.167857E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.783 | TFLOPs: 20.25 | +31: iteration 21610/ 39672 | consumed samples: 5532160 | consumed tokens: 11329863680 | elapsed time per iteration (s): 0.83 | learning rate: 9.869E-05 | global batch size: 256 | lm loss: 2.181163E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.813 | TFLOPs: 18.74 | +31: iteration 21620/ 39672 | consumed samples: 5534720 | consumed tokens: 11335106560 | elapsed time per iteration (s): 0.82 | learning rate: 9.862E-05 | global batch size: 256 | lm loss: 2.175480E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.674 | TFLOPs: 18.86 | +31: iteration 21630/ 39672 | consumed samples: 5537280 | consumed tokens: 11340349440 | elapsed time per iteration (s): 0.80 | learning rate: 9.855E-05 | global batch size: 256 | lm loss: 2.186189E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.075 | TFLOPs: 19.30 | +31: iteration 21640/ 39672 | consumed samples: 5539840 | consumed tokens: 11345592320 | elapsed time per iteration (s): 0.82 | learning rate: 9.848E-05 | global batch size: 256 | lm loss: 2.169887E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.356 | TFLOPs: 18.96 | +31: iteration 21650/ 39672 | consumed samples: 5542400 | consumed tokens: 11350835200 | elapsed time per iteration (s): 0.84 | learning rate: 9.840E-05 | global batch size: 256 | lm loss: 2.147744E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.051 | TFLOPs: 18.52 | +31: iteration 21660/ 39672 | consumed samples: 5544960 | consumed tokens: 11356078080 | elapsed time per iteration (s): 0.84 | learning rate: 9.833E-05 | global batch size: 256 | lm loss: 2.162029E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.865 | TFLOPs: 18.44 | +31: iteration 21670/ 39672 | consumed samples: 5547520 | consumed tokens: 11361320960 | elapsed time per iteration (s): 0.84 | learning rate: 9.826E-05 | global batch size: 256 | lm loss: 2.125430E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.425 | TFLOPs: 18.54 | +31: iteration 21680/ 39672 | consumed samples: 5550080 | consumed tokens: 11366563840 | elapsed time per iteration (s): 0.83 | learning rate: 9.819E-05 | global batch size: 256 | lm loss: 2.162904E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.215 | TFLOPs: 18.65 | +31: iteration 21690/ 39672 | consumed samples: 5552640 | consumed tokens: 11371806720 | elapsed time per iteration (s): 0.81 | learning rate: 9.812E-05 | global batch size: 256 | lm loss: 2.135716E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.416 | TFLOPs: 19.14 | +31: iteration 21700/ 39672 | consumed samples: 5555200 | consumed tokens: 11377049600 | elapsed time per iteration (s): 0.78 | learning rate: 9.805E-05 | global batch size: 256 | lm loss: 2.126413E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.632 | TFLOPs: 19.76 | +31: iteration 21710/ 39672 | consumed samples: 5557760 | consumed tokens: 11382292480 | elapsed time per iteration (s): 0.78 | learning rate: 9.798E-05 | global batch size: 256 | lm loss: 2.140723E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.451 | TFLOPs: 19.75 | +31: iteration 21720/ 39672 | consumed samples: 5560320 | consumed tokens: 11387535360 | elapsed time per iteration (s): 0.82 | learning rate: 9.791E-05 | global batch size: 256 | lm loss: 2.153896E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.694 | TFLOPs: 18.80 | +31: iteration 21730/ 39672 | consumed samples: 5562880 | consumed tokens: 11392778240 | elapsed time per iteration (s): 0.78 | learning rate: 9.783E-05 | global batch size: 256 | lm loss: 2.143375E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.517 | TFLOPs: 19.81 | +31: iteration 21740/ 39672 | consumed samples: 5565440 | consumed tokens: 11398021120 | elapsed time per iteration (s): 0.79 | learning rate: 9.776E-05 | global batch size: 256 | lm loss: 2.126554E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.208 | TFLOPs: 19.61 | +31: iteration 21750/ 39672 | consumed samples: 5568000 | consumed tokens: 11403264000 | elapsed time per iteration (s): 0.82 | learning rate: 9.769E-05 | global batch size: 256 | lm loss: 2.150227E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.866 | TFLOPs: 18.87 | +31: iteration 21760/ 39672 | consumed samples: 5570560 | consumed tokens: 11408506880 | elapsed time per iteration (s): 0.80 | learning rate: 9.762E-05 | global batch size: 256 | lm loss: 2.168048E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.142 | TFLOPs: 19.43 | +31: iteration 21770/ 39672 | consumed samples: 5573120 | consumed tokens: 11413749760 | elapsed time per iteration (s): 0.81 | learning rate: 9.755E-05 | global batch size: 256 | lm loss: 2.148683E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.703 | TFLOPs: 19.22 | +31: iteration 21780/ 39672 | consumed samples: 5575680 | consumed tokens: 11418992640 | elapsed time per iteration (s): 0.81 | learning rate: 9.748E-05 | global batch size: 256 | lm loss: 2.141042E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.404 | TFLOPs: 19.14 | +31: iteration 21790/ 39672 | consumed samples: 5578240 | consumed tokens: 11424235520 | elapsed time per iteration (s): 0.82 | learning rate: 9.741E-05 | global batch size: 256 | lm loss: 2.158112E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.856 | TFLOPs: 18.87 | +31: iteration 21800/ 39672 | consumed samples: 5580800 | consumed tokens: 11429478400 | elapsed time per iteration (s): 0.72 | learning rate: 9.733E-05 | global batch size: 256 | lm loss: 2.158761E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.297 | TFLOPs: 21.43 | +31: iteration 21810/ 39672 | consumed samples: 5583360 | consumed tokens: 11434721280 | elapsed time per iteration (s): 0.79 | learning rate: 9.726E-05 | global batch size: 256 | lm loss: 2.144853E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.483 | TFLOPs: 19.63 | +31: iteration 21820/ 39672 | consumed samples: 5585920 | consumed tokens: 11439964160 | elapsed time per iteration (s): 0.79 | learning rate: 9.719E-05 | global batch size: 256 | lm loss: 2.156554E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.539 | TFLOPs: 19.63 | +31: iteration 21830/ 39672 | consumed samples: 5588480 | consumed tokens: 11445207040 | elapsed time per iteration (s): 0.76 | learning rate: 9.712E-05 | global batch size: 256 | lm loss: 2.164867E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.567 | TFLOPs: 20.30 | +31: iteration 21840/ 39672 | consumed samples: 5591040 | consumed tokens: 11450449920 | elapsed time per iteration (s): 0.78 | learning rate: 9.705E-05 | global batch size: 256 | lm loss: 2.164340E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.855 | TFLOPs: 19.77 | +31: iteration 21850/ 39672 | consumed samples: 5593600 | consumed tokens: 11455692800 | elapsed time per iteration (s): 0.74 | learning rate: 9.698E-05 | global batch size: 256 | lm loss: 2.179157E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.290 | TFLOPs: 20.89 | +31: iteration 21860/ 39672 | consumed samples: 5596160 | consumed tokens: 11460935680 | elapsed time per iteration (s): 0.79 | learning rate: 9.691E-05 | global batch size: 256 | lm loss: 2.181053E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.543 | TFLOPs: 19.51 | +31: iteration 21870/ 39672 | consumed samples: 5598720 | consumed tokens: 11466178560 | elapsed time per iteration (s): 0.75 | learning rate: 9.684E-05 | global batch size: 256 | lm loss: 2.172524E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.399 | TFLOPs: 20.71 | +31: iteration 21880/ 39672 | consumed samples: 5601280 | consumed tokens: 11471421440 | elapsed time per iteration (s): 0.77 | learning rate: 9.676E-05 | global batch size: 256 | lm loss: 2.138396E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.113 | TFLOPs: 20.21 | +31: iteration 21890/ 39672 | consumed samples: 5603840 | consumed tokens: 11476664320 | elapsed time per iteration (s): 0.71 | learning rate: 9.669E-05 | global batch size: 256 | lm loss: 2.133378E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 358.310 | TFLOPs: 21.68 | +31: iteration 21900/ 39672 | consumed samples: 5606400 | consumed tokens: 11481907200 | elapsed time per iteration (s): 0.76 | learning rate: 9.662E-05 | global batch size: 256 | lm loss: 2.171415E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.204 | TFLOPs: 20.28 | +31: iteration 21910/ 39672 | consumed samples: 5608960 | consumed tokens: 11487150080 | elapsed time per iteration (s): 0.79 | learning rate: 9.655E-05 | global batch size: 256 | lm loss: 2.162197E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.988 | TFLOPs: 19.72 | +31: iteration 21920/ 39672 | consumed samples: 5611520 | consumed tokens: 11492392960 | elapsed time per iteration (s): 0.73 | learning rate: 9.648E-05 | global batch size: 256 | lm loss: 2.136447E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.384 | TFLOPs: 21.14 | +31: iteration 21930/ 39672 | consumed samples: 5614080 | consumed tokens: 11497635840 | elapsed time per iteration (s): 0.80 | learning rate: 9.641E-05 | global batch size: 256 | lm loss: 2.139748E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.403 | TFLOPs: 19.32 | +31: iteration 21940/ 39672 | consumed samples: 5616640 | consumed tokens: 11502878720 | elapsed time per iteration (s): 0.78 | learning rate: 9.634E-05 | global batch size: 256 | lm loss: 2.179636E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.601 | TFLOPs: 19.76 | +31: iteration 21950/ 39672 | consumed samples: 5619200 | consumed tokens: 11508121600 | elapsed time per iteration (s): 0.76 | learning rate: 9.627E-05 | global batch size: 256 | lm loss: 2.176951E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.136 | TFLOPs: 20.34 | +31: iteration 21960/ 39672 | consumed samples: 5621760 | consumed tokens: 11513364480 | elapsed time per iteration (s): 0.75 | learning rate: 9.620E-05 | global batch size: 256 | lm loss: 2.166452E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.121 | TFLOPs: 20.64 | +31: iteration 21970/ 39672 | consumed samples: 5624320 | consumed tokens: 11518607360 | elapsed time per iteration (s): 0.77 | learning rate: 9.612E-05 | global batch size: 256 | lm loss: 2.166415E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.201 | TFLOPs: 20.16 | +31: iteration 21980/ 39672 | consumed samples: 5626880 | consumed tokens: 11523850240 | elapsed time per iteration (s): 0.79 | learning rate: 9.605E-05 | global batch size: 256 | lm loss: 2.144544E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.660 | TFLOPs: 19.58 | +31: iteration 21990/ 39672 | consumed samples: 5629440 | consumed tokens: 11529093120 | elapsed time per iteration (s): 0.80 | learning rate: 9.598E-05 | global batch size: 256 | lm loss: 2.186627E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.141 | TFLOPs: 19.37 | + 0: [2022-11-30 14:05:23,120] [INFO] [logging.py:68:log_dist] [Rank 0] step=22000, skipped=0, lr=[9.591092308069929e-05, 9.591092308069929e-05, 9.591092308069929e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 22000/ 39672 | consumed samples: 5632000 | consumed tokens: 11534336000 | elapsed time per iteration (s): 0.78 | learning rate: 9.591E-05 | global batch size: 256 | lm loss: 2.144435E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.285 | TFLOPs: 19.98 | + 0: steps: 22000 loss: 2.1304 iter time (s): 0.808 samples/sec: 316.829 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 22000 | lm loss value: 2.106098E+00 | lm loss PPL: 8.216119E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 22010/ 39672 | consumed samples: 5634560 | consumed tokens: 11539578880 | elapsed time per iteration (s): 0.81 | learning rate: 9.584E-05 | global batch size: 256 | lm loss: 2.155117E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.574 | TFLOPs: 19.03 | +31: iteration 22020/ 39672 | consumed samples: 5637120 | consumed tokens: 11544821760 | elapsed time per iteration (s): 0.75 | learning rate: 9.577E-05 | global batch size: 256 | lm loss: 2.153880E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.626 | TFLOPs: 20.73 | +31: iteration 22030/ 39672 | consumed samples: 5639680 | consumed tokens: 11550064640 | elapsed time per iteration (s): 0.77 | learning rate: 9.570E-05 | global batch size: 256 | lm loss: 2.160657E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.617 | TFLOPs: 20.12 | +31: iteration 22040/ 39672 | consumed samples: 5642240 | consumed tokens: 11555307520 | elapsed time per iteration (s): 0.74 | learning rate: 9.563E-05 | global batch size: 256 | lm loss: 2.121943E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.747 | TFLOPs: 20.80 | +31: iteration 22050/ 39672 | consumed samples: 5644800 | consumed tokens: 11560550400 | elapsed time per iteration (s): 0.78 | learning rate: 9.556E-05 | global batch size: 256 | lm loss: 2.143717E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.014 | TFLOPs: 19.78 | +31: iteration 22060/ 39672 | consumed samples: 5647360 | consumed tokens: 11565793280 | elapsed time per iteration (s): 0.83 | learning rate: 9.548E-05 | global batch size: 256 | lm loss: 2.151252E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.804 | TFLOPs: 18.68 | +31: iteration 22070/ 39672 | consumed samples: 5649920 | consumed tokens: 11571036160 | elapsed time per iteration (s): 0.80 | learning rate: 9.541E-05 | global batch size: 256 | lm loss: 2.133356E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.781 | TFLOPs: 19.47 | +31: iteration 22080/ 39672 | consumed samples: 5652480 | consumed tokens: 11576279040 | elapsed time per iteration (s): 0.81 | learning rate: 9.534E-05 | global batch size: 256 | lm loss: 2.162053E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.046 | TFLOPs: 19.12 | +31: iteration 22090/ 39672 | consumed samples: 5655040 | consumed tokens: 11581521920 | elapsed time per iteration (s): 0.75 | learning rate: 9.527E-05 | global batch size: 256 | lm loss: 2.165254E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.701 | TFLOPs: 20.67 | +31: iteration 22100/ 39672 | consumed samples: 5657600 | consumed tokens: 11586764800 | elapsed time per iteration (s): 0.72 | learning rate: 9.520E-05 | global batch size: 256 | lm loss: 2.163084E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.928 | TFLOPs: 21.53 | +31: iteration 22110/ 39672 | consumed samples: 5660160 | consumed tokens: 11592007680 | elapsed time per iteration (s): 0.77 | learning rate: 9.513E-05 | global batch size: 256 | lm loss: 2.165882E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.416 | TFLOPs: 20.17 | +31: iteration 22120/ 39672 | consumed samples: 5662720 | consumed tokens: 11597250560 | elapsed time per iteration (s): 0.75 | learning rate: 9.506E-05 | global batch size: 256 | lm loss: 2.159249E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.844 | TFLOPs: 20.74 | +31: iteration 22130/ 39672 | consumed samples: 5665280 | consumed tokens: 11602493440 | elapsed time per iteration (s): 0.77 | learning rate: 9.499E-05 | global batch size: 256 | lm loss: 2.170151E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.597 | TFLOPs: 20.12 | +31: iteration 22140/ 39672 | consumed samples: 5667840 | consumed tokens: 11607736320 | elapsed time per iteration (s): 0.74 | learning rate: 9.492E-05 | global batch size: 256 | lm loss: 2.118445E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.582 | TFLOPs: 20.97 | +31: iteration 22150/ 39672 | consumed samples: 5670400 | consumed tokens: 11612979200 | elapsed time per iteration (s): 0.80 | learning rate: 9.485E-05 | global batch size: 256 | lm loss: 2.143728E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.612 | TFLOPs: 19.46 | +31: iteration 22160/ 39672 | consumed samples: 5672960 | consumed tokens: 11618222080 | elapsed time per iteration (s): 0.79 | learning rate: 9.477E-05 | global batch size: 256 | lm loss: 2.176193E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.758 | TFLOPs: 19.71 | +31: iteration 22170/ 39672 | consumed samples: 5675520 | consumed tokens: 11623464960 | elapsed time per iteration (s): 0.79 | learning rate: 9.470E-05 | global batch size: 256 | lm loss: 2.124782E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.145 | TFLOPs: 19.49 | +31: iteration 22180/ 39672 | consumed samples: 5678080 | consumed tokens: 11628707840 | elapsed time per iteration (s): 0.83 | learning rate: 9.463E-05 | global batch size: 256 | lm loss: 2.160888E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.355 | TFLOPs: 18.72 | +31: iteration 22190/ 39672 | consumed samples: 5680640 | consumed tokens: 11633950720 | elapsed time per iteration (s): 0.79 | learning rate: 9.456E-05 | global batch size: 256 | lm loss: 2.173138E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.881 | TFLOPs: 19.59 | +31: iteration 22200/ 39672 | consumed samples: 5683200 | consumed tokens: 11639193600 | elapsed time per iteration (s): 0.80 | learning rate: 9.449E-05 | global batch size: 256 | lm loss: 2.148606E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.908 | TFLOPs: 19.47 | +31: iteration 22210/ 39672 | consumed samples: 5685760 | consumed tokens: 11644436480 | elapsed time per iteration (s): 0.80 | learning rate: 9.442E-05 | global batch size: 256 | lm loss: 2.166194E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.549 | TFLOPs: 19.27 | +31: iteration 22220/ 39672 | consumed samples: 5688320 | consumed tokens: 11649679360 | elapsed time per iteration (s): 0.82 | learning rate: 9.435E-05 | global batch size: 256 | lm loss: 2.146686E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.041 | TFLOPs: 18.88 | +31: iteration 22230/ 39672 | consumed samples: 5690880 | consumed tokens: 11654922240 | elapsed time per iteration (s): 0.82 | learning rate: 9.428E-05 | global batch size: 256 | lm loss: 2.168548E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.573 | TFLOPs: 18.97 | +31: iteration 22240/ 39672 | consumed samples: 5693440 | consumed tokens: 11660165120 | elapsed time per iteration (s): 0.80 | learning rate: 9.421E-05 | global batch size: 256 | lm loss: 2.168913E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.506 | TFLOPs: 19.33 | +31: iteration 22250/ 39672 | consumed samples: 5696000 | consumed tokens: 11665408000 | elapsed time per iteration (s): 0.76 | learning rate: 9.414E-05 | global batch size: 256 | lm loss: 2.115911E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.954 | TFLOPs: 20.51 | +31: iteration 22260/ 39672 | consumed samples: 5698560 | consumed tokens: 11670650880 | elapsed time per iteration (s): 0.74 | learning rate: 9.407E-05 | global batch size: 256 | lm loss: 2.156266E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.409 | TFLOPs: 20.84 | +31: iteration 22270/ 39672 | consumed samples: 5701120 | consumed tokens: 11675893760 | elapsed time per iteration (s): 0.77 | learning rate: 9.399E-05 | global batch size: 256 | lm loss: 2.173890E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.133 | TFLOPs: 20.03 | +31: iteration 22280/ 39672 | consumed samples: 5703680 | consumed tokens: 11681136640 | elapsed time per iteration (s): 0.78 | learning rate: 9.392E-05 | global batch size: 256 | lm loss: 2.171398E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.117 | TFLOPs: 19.91 | +31: iteration 22290/ 39672 | consumed samples: 5706240 | consumed tokens: 11686379520 | elapsed time per iteration (s): 0.79 | learning rate: 9.385E-05 | global batch size: 256 | lm loss: 2.193473E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.092 | TFLOPs: 19.73 | +31: iteration 22300/ 39672 | consumed samples: 5708800 | consumed tokens: 11691622400 | elapsed time per iteration (s): 0.74 | learning rate: 9.378E-05 | global batch size: 256 | lm loss: 2.135098E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.461 | TFLOPs: 20.90 | +31: iteration 22310/ 39672 | consumed samples: 5711360 | consumed tokens: 11696865280 | elapsed time per iteration (s): 0.79 | learning rate: 9.371E-05 | global batch size: 256 | lm loss: 2.150255E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.878 | TFLOPs: 19.65 | +31: iteration 22320/ 39672 | consumed samples: 5713920 | consumed tokens: 11702108160 | elapsed time per iteration (s): 0.76 | learning rate: 9.364E-05 | global batch size: 256 | lm loss: 2.133369E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.813 | TFLOPs: 20.50 | +31: iteration 22330/ 39672 | consumed samples: 5716480 | consumed tokens: 11707351040 | elapsed time per iteration (s): 0.77 | learning rate: 9.357E-05 | global batch size: 256 | lm loss: 2.159064E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.037 | TFLOPs: 20.15 | +31: iteration 22340/ 39672 | consumed samples: 5719040 | consumed tokens: 11712593920 | elapsed time per iteration (s): 0.74 | learning rate: 9.350E-05 | global batch size: 256 | lm loss: 2.139133E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.553 | TFLOPs: 20.91 | +31: iteration 22350/ 39672 | consumed samples: 5721600 | consumed tokens: 11717836800 | elapsed time per iteration (s): 0.76 | learning rate: 9.343E-05 | global batch size: 256 | lm loss: 2.109044E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.260 | TFLOPs: 20.46 | +31: iteration 22360/ 39672 | consumed samples: 5724160 | consumed tokens: 11723079680 | elapsed time per iteration (s): 0.72 | learning rate: 9.336E-05 | global batch size: 256 | lm loss: 2.151180E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.827 | TFLOPs: 21.59 | +31: iteration 22370/ 39672 | consumed samples: 5726720 | consumed tokens: 11728322560 | elapsed time per iteration (s): 0.75 | learning rate: 9.329E-05 | global batch size: 256 | lm loss: 2.148763E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.186 | TFLOPs: 20.70 | +31: iteration 22380/ 39672 | consumed samples: 5729280 | consumed tokens: 11733565440 | elapsed time per iteration (s): 0.76 | learning rate: 9.322E-05 | global batch size: 256 | lm loss: 2.139706E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.747 | TFLOPs: 20.49 | +31: iteration 22390/ 39672 | consumed samples: 5731840 | consumed tokens: 11738808320 | elapsed time per iteration (s): 0.76 | learning rate: 9.315E-05 | global batch size: 256 | lm loss: 2.104637E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.659 | TFLOPs: 20.31 | +31: iteration 22400/ 39672 | consumed samples: 5734400 | consumed tokens: 11744051200 | elapsed time per iteration (s): 0.74 | learning rate: 9.307E-05 | global batch size: 256 | lm loss: 2.144266E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.459 | TFLOPs: 20.90 | +31: iteration 22410/ 39672 | consumed samples: 5736960 | consumed tokens: 11749294080 | elapsed time per iteration (s): 0.78 | learning rate: 9.300E-05 | global batch size: 256 | lm loss: 2.143990E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.304 | TFLOPs: 19.74 | +31: iteration 22420/ 39672 | consumed samples: 5739520 | consumed tokens: 11754536960 | elapsed time per iteration (s): 0.75 | learning rate: 9.293E-05 | global batch size: 256 | lm loss: 2.121547E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.500 | TFLOPs: 20.78 | +31: iteration 22430/ 39672 | consumed samples: 5742080 | consumed tokens: 11759779840 | elapsed time per iteration (s): 0.73 | learning rate: 9.286E-05 | global batch size: 256 | lm loss: 2.119294E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.345 | TFLOPs: 21.19 | +31: iteration 22440/ 39672 | consumed samples: 5744640 | consumed tokens: 11765022720 | elapsed time per iteration (s): 0.78 | learning rate: 9.279E-05 | global batch size: 256 | lm loss: 2.150871E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.773 | TFLOPs: 19.77 | +31: iteration 22450/ 39672 | consumed samples: 5747200 | consumed tokens: 11770265600 | elapsed time per iteration (s): 0.79 | learning rate: 9.272E-05 | global batch size: 256 | lm loss: 2.164017E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.415 | TFLOPs: 19.69 | +31: iteration 22460/ 39672 | consumed samples: 5749760 | consumed tokens: 11775508480 | elapsed time per iteration (s): 0.79 | learning rate: 9.265E-05 | global batch size: 256 | lm loss: 2.162876E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.335 | TFLOPs: 19.56 | +31: iteration 22470/ 39672 | consumed samples: 5752320 | consumed tokens: 11780751360 | elapsed time per iteration (s): 0.74 | learning rate: 9.258E-05 | global batch size: 256 | lm loss: 2.165226E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.254 | TFLOPs: 20.95 | +31: iteration 22480/ 39672 | consumed samples: 5754880 | consumed tokens: 11785994240 | elapsed time per iteration (s): 0.80 | learning rate: 9.251E-05 | global batch size: 256 | lm loss: 2.140035E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.645 | TFLOPs: 19.28 | +31: iteration 22490/ 39672 | consumed samples: 5757440 | consumed tokens: 11791237120 | elapsed time per iteration (s): 0.75 | learning rate: 9.244E-05 | global batch size: 256 | lm loss: 2.130819E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.426 | TFLOPs: 20.72 | +31: iteration 22500/ 39672 | consumed samples: 5760000 | consumed tokens: 11796480000 | elapsed time per iteration (s): 0.78 | learning rate: 9.237E-05 | global batch size: 256 | lm loss: 2.151355E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.174 | TFLOPs: 19.73 | +31: iteration 22510/ 39672 | consumed samples: 5762560 | consumed tokens: 11801722880 | elapsed time per iteration (s): 0.80 | learning rate: 9.230E-05 | global batch size: 256 | lm loss: 2.160586E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.768 | TFLOPs: 19.35 | +31: iteration 22520/ 39672 | consumed samples: 5765120 | consumed tokens: 11806965760 | elapsed time per iteration (s): 0.75 | learning rate: 9.223E-05 | global batch size: 256 | lm loss: 2.180851E+00 | grad norm: 1.509 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.737 | TFLOPs: 20.61 | +31: iteration 22530/ 39672 | consumed samples: 5767680 | consumed tokens: 11812208640 | elapsed time per iteration (s): 0.77 | learning rate: 9.216E-05 | global batch size: 256 | lm loss: 2.189850E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.987 | TFLOPs: 20.21 | +31: iteration 22540/ 39672 | consumed samples: 5770240 | consumed tokens: 11817451520 | elapsed time per iteration (s): 0.79 | learning rate: 9.209E-05 | global batch size: 256 | lm loss: 2.167402E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.056 | TFLOPs: 19.67 | +31: iteration 22550/ 39672 | consumed samples: 5772800 | consumed tokens: 11822694400 | elapsed time per iteration (s): 0.80 | learning rate: 9.202E-05 | global batch size: 256 | lm loss: 2.195003E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.156 | TFLOPs: 19.31 | +31: iteration 22560/ 39672 | consumed samples: 5775360 | consumed tokens: 11827937280 | elapsed time per iteration (s): 0.74 | learning rate: 9.194E-05 | global batch size: 256 | lm loss: 2.147572E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.548 | TFLOPs: 20.97 | +31: iteration 22570/ 39672 | consumed samples: 5777920 | consumed tokens: 11833180160 | elapsed time per iteration (s): 0.73 | learning rate: 9.187E-05 | global batch size: 256 | lm loss: 2.146683E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.085 | TFLOPs: 21.18 | +31: iteration 22580/ 39672 | consumed samples: 5780480 | consumed tokens: 11838423040 | elapsed time per iteration (s): 0.74 | learning rate: 9.180E-05 | global batch size: 256 | lm loss: 2.129647E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.705 | TFLOPs: 20.97 | +31: iteration 22590/ 39672 | consumed samples: 5783040 | consumed tokens: 11843665920 | elapsed time per iteration (s): 0.71 | learning rate: 9.173E-05 | global batch size: 256 | lm loss: 2.147986E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 361.514 | TFLOPs: 21.87 | +31: iteration 22600/ 39672 | consumed samples: 5785600 | consumed tokens: 11848908800 | elapsed time per iteration (s): 0.78 | learning rate: 9.166E-05 | global batch size: 256 | lm loss: 2.155142E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.285 | TFLOPs: 19.98 | +31: iteration 22610/ 39672 | consumed samples: 5788160 | consumed tokens: 11854151680 | elapsed time per iteration (s): 0.81 | learning rate: 9.159E-05 | global batch size: 256 | lm loss: 2.131115E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.360 | TFLOPs: 19.08 | +31: iteration 22620/ 39672 | consumed samples: 5790720 | consumed tokens: 11859394560 | elapsed time per iteration (s): 0.78 | learning rate: 9.152E-05 | global batch size: 256 | lm loss: 2.143242E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.672 | TFLOPs: 19.82 | +31: iteration 22630/ 39672 | consumed samples: 5793280 | consumed tokens: 11864637440 | elapsed time per iteration (s): 0.79 | learning rate: 9.145E-05 | global batch size: 256 | lm loss: 2.172000E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.198 | TFLOPs: 19.67 | +31: iteration 22640/ 39672 | consumed samples: 5795840 | consumed tokens: 11869880320 | elapsed time per iteration (s): 0.76 | learning rate: 9.138E-05 | global batch size: 256 | lm loss: 2.139146E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.517 | TFLOPs: 20.36 | +31: iteration 22650/ 39672 | consumed samples: 5798400 | consumed tokens: 11875123200 | elapsed time per iteration (s): 0.80 | learning rate: 9.131E-05 | global batch size: 256 | lm loss: 2.145883E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.641 | TFLOPs: 19.46 | +31: iteration 22660/ 39672 | consumed samples: 5800960 | consumed tokens: 11880366080 | elapsed time per iteration (s): 0.80 | learning rate: 9.124E-05 | global batch size: 256 | lm loss: 2.145083E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.099 | TFLOPs: 19.37 | +31: iteration 22670/ 39672 | consumed samples: 5803520 | consumed tokens: 11885608960 | elapsed time per iteration (s): 0.80 | learning rate: 9.117E-05 | global batch size: 256 | lm loss: 2.140424E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.012 | TFLOPs: 19.42 | +31: iteration 22680/ 39672 | consumed samples: 5806080 | consumed tokens: 11890851840 | elapsed time per iteration (s): 0.86 | learning rate: 9.110E-05 | global batch size: 256 | lm loss: 2.162826E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.801 | TFLOPs: 18.02 | +31: iteration 22690/ 39672 | consumed samples: 5808640 | consumed tokens: 11896094720 | elapsed time per iteration (s): 0.88 | learning rate: 9.103E-05 | global batch size: 256 | lm loss: 2.174326E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 292.504 | TFLOPs: 17.70 | +31: iteration 22700/ 39672 | consumed samples: 5811200 | consumed tokens: 11901337600 | elapsed time per iteration (s): 0.79 | learning rate: 9.096E-05 | global batch size: 256 | lm loss: 2.148481E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.337 | TFLOPs: 19.50 | +31: iteration 22710/ 39672 | consumed samples: 5813760 | consumed tokens: 11906580480 | elapsed time per iteration (s): 0.74 | learning rate: 9.089E-05 | global batch size: 256 | lm loss: 2.170101E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.524 | TFLOPs: 20.96 | +31: iteration 22720/ 39672 | consumed samples: 5816320 | consumed tokens: 11911823360 | elapsed time per iteration (s): 0.76 | learning rate: 9.082E-05 | global batch size: 256 | lm loss: 2.132868E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.383 | TFLOPs: 20.35 | +31: iteration 22730/ 39672 | consumed samples: 5818880 | consumed tokens: 11917066240 | elapsed time per iteration (s): 0.76 | learning rate: 9.075E-05 | global batch size: 256 | lm loss: 2.127784E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.181 | TFLOPs: 20.34 | +31: iteration 22740/ 39672 | consumed samples: 5821440 | consumed tokens: 11922309120 | elapsed time per iteration (s): 0.73 | learning rate: 9.068E-05 | global batch size: 256 | lm loss: 2.132083E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.301 | TFLOPs: 21.19 | +31: iteration 22750/ 39672 | consumed samples: 5824000 | consumed tokens: 11927552000 | elapsed time per iteration (s): 0.71 | learning rate: 9.061E-05 | global batch size: 256 | lm loss: 2.119333E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.601 | TFLOPs: 21.75 | +31: iteration 22760/ 39672 | consumed samples: 5826560 | consumed tokens: 11932794880 | elapsed time per iteration (s): 0.75 | learning rate: 9.054E-05 | global batch size: 256 | lm loss: 2.183520E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.336 | TFLOPs: 20.53 | +31: iteration 22770/ 39672 | consumed samples: 5829120 | consumed tokens: 11938037760 | elapsed time per iteration (s): 0.79 | learning rate: 9.047E-05 | global batch size: 256 | lm loss: 2.160817E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.397 | TFLOPs: 19.63 | +31: iteration 22780/ 39672 | consumed samples: 5831680 | consumed tokens: 11943280640 | elapsed time per iteration (s): 0.77 | learning rate: 9.040E-05 | global batch size: 256 | lm loss: 2.159649E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.767 | TFLOPs: 20.13 | +31: iteration 22790/ 39672 | consumed samples: 5834240 | consumed tokens: 11948523520 | elapsed time per iteration (s): 0.76 | learning rate: 9.033E-05 | global batch size: 256 | lm loss: 2.165467E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.418 | TFLOPs: 20.29 | +31: iteration 22800/ 39672 | consumed samples: 5836800 | consumed tokens: 11953766400 | elapsed time per iteration (s): 0.83 | learning rate: 9.026E-05 | global batch size: 256 | lm loss: 2.147651E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.359 | TFLOPs: 18.59 | +31: iteration 22810/ 39672 | consumed samples: 5839360 | consumed tokens: 11959009280 | elapsed time per iteration (s): 0.74 | learning rate: 9.019E-05 | global batch size: 256 | lm loss: 2.152770E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.789 | TFLOPs: 21.04 | +31: iteration 22820/ 39672 | consumed samples: 5841920 | consumed tokens: 11964252160 | elapsed time per iteration (s): 0.76 | learning rate: 9.012E-05 | global batch size: 256 | lm loss: 2.151168E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.892 | TFLOPs: 20.26 | +31: iteration 22830/ 39672 | consumed samples: 5844480 | consumed tokens: 11969495040 | elapsed time per iteration (s): 0.77 | learning rate: 9.004E-05 | global batch size: 256 | lm loss: 2.154842E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.424 | TFLOPs: 20.11 | +31: iteration 22840/ 39672 | consumed samples: 5847040 | consumed tokens: 11974737920 | elapsed time per iteration (s): 0.80 | learning rate: 8.997E-05 | global batch size: 256 | lm loss: 2.130728E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.566 | TFLOPs: 19.39 | +31: iteration 22850/ 39672 | consumed samples: 5849600 | consumed tokens: 11979980800 | elapsed time per iteration (s): 0.78 | learning rate: 8.990E-05 | global batch size: 256 | lm loss: 2.155223E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.136 | TFLOPs: 19.79 | +31: iteration 22860/ 39672 | consumed samples: 5852160 | consumed tokens: 11985223680 | elapsed time per iteration (s): 0.74 | learning rate: 8.983E-05 | global batch size: 256 | lm loss: 2.129053E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.692 | TFLOPs: 20.91 | +31: iteration 22870/ 39672 | consumed samples: 5854720 | consumed tokens: 11990466560 | elapsed time per iteration (s): 0.75 | learning rate: 8.976E-05 | global batch size: 256 | lm loss: 2.159210E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.788 | TFLOPs: 20.68 | +31: iteration 22880/ 39672 | consumed samples: 5857280 | consumed tokens: 11995709440 | elapsed time per iteration (s): 0.81 | learning rate: 8.969E-05 | global batch size: 256 | lm loss: 2.168676E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.646 | TFLOPs: 19.16 | +31: iteration 22890/ 39672 | consumed samples: 5859840 | consumed tokens: 12000952320 | elapsed time per iteration (s): 0.75 | learning rate: 8.962E-05 | global batch size: 256 | lm loss: 2.142551E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.233 | TFLOPs: 20.58 | +31: iteration 22900/ 39672 | consumed samples: 5862400 | consumed tokens: 12006195200 | elapsed time per iteration (s): 0.76 | learning rate: 8.955E-05 | global batch size: 256 | lm loss: 2.166534E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.594 | TFLOPs: 20.42 | +31: iteration 22910/ 39672 | consumed samples: 5864960 | consumed tokens: 12011438080 | elapsed time per iteration (s): 0.77 | learning rate: 8.948E-05 | global batch size: 256 | lm loss: 2.140992E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.300 | TFLOPs: 20.22 | +31: iteration 22920/ 39672 | consumed samples: 5867520 | consumed tokens: 12016680960 | elapsed time per iteration (s): 0.81 | learning rate: 8.941E-05 | global batch size: 256 | lm loss: 2.154667E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.346 | TFLOPs: 19.02 | +31: iteration 22930/ 39672 | consumed samples: 5870080 | consumed tokens: 12021923840 | elapsed time per iteration (s): 0.79 | learning rate: 8.934E-05 | global batch size: 256 | lm loss: 2.146514E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.066 | TFLOPs: 19.73 | +31: iteration 22940/ 39672 | consumed samples: 5872640 | consumed tokens: 12027166720 | elapsed time per iteration (s): 0.82 | learning rate: 8.927E-05 | global batch size: 256 | lm loss: 2.109872E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.696 | TFLOPs: 18.80 | +31: iteration 22950/ 39672 | consumed samples: 5875200 | consumed tokens: 12032409600 | elapsed time per iteration (s): 0.79 | learning rate: 8.920E-05 | global batch size: 256 | lm loss: 2.136150E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.760 | TFLOPs: 19.65 | +31: iteration 22960/ 39672 | consumed samples: 5877760 | consumed tokens: 12037652480 | elapsed time per iteration (s): 0.80 | learning rate: 8.913E-05 | global batch size: 256 | lm loss: 2.158234E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.142 | TFLOPs: 19.37 | +31: iteration 22970/ 39672 | consumed samples: 5880320 | consumed tokens: 12042895360 | elapsed time per iteration (s): 0.79 | learning rate: 8.906E-05 | global batch size: 256 | lm loss: 2.121021E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.874 | TFLOPs: 19.59 | +31: iteration 22980/ 39672 | consumed samples: 5882880 | consumed tokens: 12048138240 | elapsed time per iteration (s): 0.79 | learning rate: 8.899E-05 | global batch size: 256 | lm loss: 2.130037E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.900 | TFLOPs: 19.53 | +31: iteration 22990/ 39672 | consumed samples: 5885440 | consumed tokens: 12053381120 | elapsed time per iteration (s): 0.79 | learning rate: 8.892E-05 | global batch size: 256 | lm loss: 2.135116E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.033 | TFLOPs: 19.60 | +31: iteration 23000/ 39672 | consumed samples: 5888000 | consumed tokens: 12058624000 | elapsed time per iteration (s): 0.74 | learning rate: 8.885E-05 | global batch size: 256 | lm loss: 2.141711E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.590 | TFLOPs: 20.85 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 23000 | lm loss value: 2.097132E+00 | lm loss PPL: 8.142787E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 23010/ 39672 | consumed samples: 5890560 | consumed tokens: 12063866880 | elapsed time per iteration (s): 0.79 | learning rate: 8.878E-05 | global batch size: 256 | lm loss: 2.151551E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.308 | TFLOPs: 19.56 | +31: iteration 23020/ 39672 | consumed samples: 5893120 | consumed tokens: 12069109760 | elapsed time per iteration (s): 0.77 | learning rate: 8.871E-05 | global batch size: 256 | lm loss: 2.135651E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.974 | TFLOPs: 20.14 | +31: iteration 23030/ 39672 | consumed samples: 5895680 | consumed tokens: 12074352640 | elapsed time per iteration (s): 0.79 | learning rate: 8.864E-05 | global batch size: 256 | lm loss: 2.136388E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.898 | TFLOPs: 19.59 | +31: iteration 23040/ 39672 | consumed samples: 5898240 | consumed tokens: 12079595520 | elapsed time per iteration (s): 0.80 | learning rate: 8.857E-05 | global batch size: 256 | lm loss: 2.138485E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.153 | TFLOPs: 19.43 | +31: iteration 23050/ 39672 | consumed samples: 5900800 | consumed tokens: 12084838400 | elapsed time per iteration (s): 0.74 | learning rate: 8.850E-05 | global batch size: 256 | lm loss: 2.117239E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.020 | TFLOPs: 21.05 | +31: iteration 23060/ 39672 | consumed samples: 5903360 | consumed tokens: 12090081280 | elapsed time per iteration (s): 0.76 | learning rate: 8.843E-05 | global batch size: 256 | lm loss: 2.165150E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.854 | TFLOPs: 20.38 | +31: iteration 23070/ 39672 | consumed samples: 5905920 | consumed tokens: 12095324160 | elapsed time per iteration (s): 0.77 | learning rate: 8.836E-05 | global batch size: 256 | lm loss: 2.136612E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.855 | TFLOPs: 20.14 | +31: iteration 23080/ 39672 | consumed samples: 5908480 | consumed tokens: 12100567040 | elapsed time per iteration (s): 0.74 | learning rate: 8.829E-05 | global batch size: 256 | lm loss: 2.163928E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.172 | TFLOPs: 20.94 | +31: iteration 23090/ 39672 | consumed samples: 5911040 | consumed tokens: 12105809920 | elapsed time per iteration (s): 0.76 | learning rate: 8.822E-05 | global batch size: 256 | lm loss: 2.117379E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.294 | TFLOPs: 20.28 | +31: iteration 23100/ 39672 | consumed samples: 5913600 | consumed tokens: 12111052800 | elapsed time per iteration (s): 0.77 | learning rate: 8.815E-05 | global batch size: 256 | lm loss: 2.133357E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.522 | TFLOPs: 20.18 | +31: iteration 23110/ 39672 | consumed samples: 5916160 | consumed tokens: 12116295680 | elapsed time per iteration (s): 0.84 | learning rate: 8.808E-05 | global batch size: 256 | lm loss: 2.129219E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.968 | TFLOPs: 18.39 | +31: iteration 23120/ 39672 | consumed samples: 5918720 | consumed tokens: 12121538560 | elapsed time per iteration (s): 0.78 | learning rate: 8.801E-05 | global batch size: 256 | lm loss: 2.119216E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.029 | TFLOPs: 19.91 | +31: iteration 23130/ 39672 | consumed samples: 5921280 | consumed tokens: 12126781440 | elapsed time per iteration (s): 0.87 | learning rate: 8.794E-05 | global batch size: 256 | lm loss: 2.183261E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.378 | TFLOPs: 17.87 | +31: iteration 23140/ 39672 | consumed samples: 5923840 | consumed tokens: 12132024320 | elapsed time per iteration (s): 0.77 | learning rate: 8.788E-05 | global batch size: 256 | lm loss: 2.133070E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.156 | TFLOPs: 20.09 | +31: iteration 23150/ 39672 | consumed samples: 5926400 | consumed tokens: 12137267200 | elapsed time per iteration (s): 0.76 | learning rate: 8.781E-05 | global batch size: 256 | lm loss: 2.119289E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.325 | TFLOPs: 20.29 | +31: iteration 23160/ 39672 | consumed samples: 5928960 | consumed tokens: 12142510080 | elapsed time per iteration (s): 0.76 | learning rate: 8.774E-05 | global batch size: 256 | lm loss: 2.106453E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.207 | TFLOPs: 20.28 | +31: iteration 23170/ 39672 | consumed samples: 5931520 | consumed tokens: 12147752960 | elapsed time per iteration (s): 0.74 | learning rate: 8.767E-05 | global batch size: 256 | lm loss: 2.159702E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.686 | TFLOPs: 20.91 | +31: iteration 23180/ 39672 | consumed samples: 5934080 | consumed tokens: 12152995840 | elapsed time per iteration (s): 0.77 | learning rate: 8.760E-05 | global batch size: 256 | lm loss: 2.152430E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.517 | TFLOPs: 20.00 | +31: iteration 23190/ 39672 | consumed samples: 5936640 | consumed tokens: 12158238720 | elapsed time per iteration (s): 0.79 | learning rate: 8.753E-05 | global batch size: 256 | lm loss: 2.171799E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.637 | TFLOPs: 19.52 | +31: iteration 23200/ 39672 | consumed samples: 5939200 | consumed tokens: 12163481600 | elapsed time per iteration (s): 0.81 | learning rate: 8.746E-05 | global batch size: 256 | lm loss: 2.147317E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.790 | TFLOPs: 19.10 | +31: iteration 23210/ 39672 | consumed samples: 5941760 | consumed tokens: 12168724480 | elapsed time per iteration (s): 0.88 | learning rate: 8.739E-05 | global batch size: 256 | lm loss: 2.128669E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 290.361 | TFLOPs: 17.57 | +31: iteration 23220/ 39672 | consumed samples: 5944320 | consumed tokens: 12173967360 | elapsed time per iteration (s): 0.74 | learning rate: 8.732E-05 | global batch size: 256 | lm loss: 2.141524E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.190 | TFLOPs: 20.94 | +31: iteration 23230/ 39672 | consumed samples: 5946880 | consumed tokens: 12179210240 | elapsed time per iteration (s): 0.74 | learning rate: 8.725E-05 | global batch size: 256 | lm loss: 2.133854E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.717 | TFLOPs: 20.85 | +31: iteration 23240/ 39672 | consumed samples: 5949440 | consumed tokens: 12184453120 | elapsed time per iteration (s): 0.78 | learning rate: 8.718E-05 | global batch size: 256 | lm loss: 2.137653E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.225 | TFLOPs: 19.98 | +31: iteration 23250/ 39672 | consumed samples: 5952000 | consumed tokens: 12189696000 | elapsed time per iteration (s): 0.78 | learning rate: 8.711E-05 | global batch size: 256 | lm loss: 2.159035E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.281 | TFLOPs: 19.98 | +31: iteration 23260/ 39672 | consumed samples: 5954560 | consumed tokens: 12194938880 | elapsed time per iteration (s): 0.79 | learning rate: 8.704E-05 | global batch size: 256 | lm loss: 2.132359E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.757 | TFLOPs: 19.65 | +31: iteration 23270/ 39672 | consumed samples: 5957120 | consumed tokens: 12200181760 | elapsed time per iteration (s): 0.83 | learning rate: 8.697E-05 | global batch size: 256 | lm loss: 2.160357E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.988 | TFLOPs: 18.57 | +31: iteration 23280/ 39672 | consumed samples: 5959680 | consumed tokens: 12205424640 | elapsed time per iteration (s): 0.77 | learning rate: 8.690E-05 | global batch size: 256 | lm loss: 2.142416E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.085 | TFLOPs: 20.09 | +31: iteration 23290/ 39672 | consumed samples: 5962240 | consumed tokens: 12210667520 | elapsed time per iteration (s): 0.84 | learning rate: 8.683E-05 | global batch size: 256 | lm loss: 2.139009E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.497 | TFLOPs: 18.54 | +31: iteration 23300/ 39672 | consumed samples: 5964800 | consumed tokens: 12215910400 | elapsed time per iteration (s): 0.80 | learning rate: 8.676E-05 | global batch size: 256 | lm loss: 2.160676E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.555 | TFLOPs: 19.27 | +31: iteration 23310/ 39672 | consumed samples: 5967360 | consumed tokens: 12221153280 | elapsed time per iteration (s): 0.84 | learning rate: 8.669E-05 | global batch size: 256 | lm loss: 2.143783E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.978 | TFLOPs: 18.39 | +31: iteration 23320/ 39672 | consumed samples: 5969920 | consumed tokens: 12226396160 | elapsed time per iteration (s): 0.81 | learning rate: 8.662E-05 | global batch size: 256 | lm loss: 2.153976E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.155 | TFLOPs: 19.07 | +31: iteration 23330/ 39672 | consumed samples: 5972480 | consumed tokens: 12231639040 | elapsed time per iteration (s): 0.86 | learning rate: 8.655E-05 | global batch size: 256 | lm loss: 2.127339E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.446 | TFLOPs: 17.99 | +31: iteration 23340/ 39672 | consumed samples: 5975040 | consumed tokens: 12236881920 | elapsed time per iteration (s): 0.83 | learning rate: 8.648E-05 | global batch size: 256 | lm loss: 2.151804E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.273 | TFLOPs: 18.65 | +31: iteration 23350/ 39672 | consumed samples: 5977600 | consumed tokens: 12242124800 | elapsed time per iteration (s): 0.84 | learning rate: 8.641E-05 | global batch size: 256 | lm loss: 2.148044E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.763 | TFLOPs: 18.38 | +31: iteration 23360/ 39672 | consumed samples: 5980160 | consumed tokens: 12247367680 | elapsed time per iteration (s): 0.82 | learning rate: 8.634E-05 | global batch size: 256 | lm loss: 2.152135E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.351 | TFLOPs: 18.84 | +31: iteration 23370/ 39672 | consumed samples: 5982720 | consumed tokens: 12252610560 | elapsed time per iteration (s): 0.80 | learning rate: 8.627E-05 | global batch size: 256 | lm loss: 2.133773E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.774 | TFLOPs: 19.41 | +31: iteration 23380/ 39672 | consumed samples: 5985280 | consumed tokens: 12257853440 | elapsed time per iteration (s): 0.81 | learning rate: 8.620E-05 | global batch size: 256 | lm loss: 2.154587E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.514 | TFLOPs: 19.03 | +31: iteration 23390/ 39672 | consumed samples: 5987840 | consumed tokens: 12263096320 | elapsed time per iteration (s): 0.80 | learning rate: 8.614E-05 | global batch size: 256 | lm loss: 2.141769E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.870 | TFLOPs: 19.41 | +31: iteration 23400/ 39672 | consumed samples: 5990400 | consumed tokens: 12268339200 | elapsed time per iteration (s): 0.78 | learning rate: 8.607E-05 | global batch size: 256 | lm loss: 2.111323E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.895 | TFLOPs: 19.84 | +31: iteration 23410/ 39672 | consumed samples: 5992960 | consumed tokens: 12273582080 | elapsed time per iteration (s): 0.80 | learning rate: 8.600E-05 | global batch size: 256 | lm loss: 2.136164E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.749 | TFLOPs: 19.34 | +31: iteration 23420/ 39672 | consumed samples: 5995520 | consumed tokens: 12278824960 | elapsed time per iteration (s): 0.83 | learning rate: 8.593E-05 | global batch size: 256 | lm loss: 2.147381E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.957 | TFLOPs: 18.57 | +31: iteration 23430/ 39672 | consumed samples: 5998080 | consumed tokens: 12284067840 | elapsed time per iteration (s): 0.79 | learning rate: 8.586E-05 | global batch size: 256 | lm loss: 2.125541E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.042 | TFLOPs: 19.72 | +31: iteration 23440/ 39672 | consumed samples: 6000640 | consumed tokens: 12289310720 | elapsed time per iteration (s): 0.75 | learning rate: 8.579E-05 | global batch size: 256 | lm loss: 2.146725E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.821 | TFLOPs: 20.68 | +31: iteration 23450/ 39672 | consumed samples: 6003200 | consumed tokens: 12294553600 | elapsed time per iteration (s): 0.80 | learning rate: 8.572E-05 | global batch size: 256 | lm loss: 2.127031E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.236 | TFLOPs: 19.25 | +31: iteration 23460/ 39672 | consumed samples: 6005760 | consumed tokens: 12299796480 | elapsed time per iteration (s): 0.78 | learning rate: 8.565E-05 | global batch size: 256 | lm loss: 2.128054E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.816 | TFLOPs: 19.95 | +31: iteration 23470/ 39672 | consumed samples: 6008320 | consumed tokens: 12305039360 | elapsed time per iteration (s): 0.79 | learning rate: 8.558E-05 | global batch size: 256 | lm loss: 2.158463E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.673 | TFLOPs: 19.52 | +31: iteration 23480/ 39672 | consumed samples: 6010880 | consumed tokens: 12310282240 | elapsed time per iteration (s): 0.76 | learning rate: 8.551E-05 | global batch size: 256 | lm loss: 2.156234E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.840 | TFLOPs: 20.44 | +31: iteration 23490/ 39672 | consumed samples: 6013440 | consumed tokens: 12315525120 | elapsed time per iteration (s): 0.78 | learning rate: 8.544E-05 | global batch size: 256 | lm loss: 2.145563E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.219 | TFLOPs: 19.86 | +31: iteration 23500/ 39672 | consumed samples: 6016000 | consumed tokens: 12320768000 | elapsed time per iteration (s): 0.76 | learning rate: 8.537E-05 | global batch size: 256 | lm loss: 2.150534E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.825 | TFLOPs: 20.38 | +31: iteration 23510/ 39672 | consumed samples: 6018560 | consumed tokens: 12326010880 | elapsed time per iteration (s): 0.78 | learning rate: 8.530E-05 | global batch size: 256 | lm loss: 2.114151E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.623 | TFLOPs: 19.88 | +31: iteration 23520/ 39672 | consumed samples: 6021120 | consumed tokens: 12331253760 | elapsed time per iteration (s): 0.78 | learning rate: 8.523E-05 | global batch size: 256 | lm loss: 2.161347E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.964 | TFLOPs: 19.78 | +31: iteration 23530/ 39672 | consumed samples: 6023680 | consumed tokens: 12336496640 | elapsed time per iteration (s): 0.76 | learning rate: 8.516E-05 | global batch size: 256 | lm loss: 2.145916E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.013 | TFLOPs: 20.27 | +31: iteration 23540/ 39672 | consumed samples: 6026240 | consumed tokens: 12341739520 | elapsed time per iteration (s): 0.77 | learning rate: 8.510E-05 | global batch size: 256 | lm loss: 2.219683E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.041 | TFLOPs: 20.03 | +31: iteration 23550/ 39672 | consumed samples: 6028800 | consumed tokens: 12346982400 | elapsed time per iteration (s): 0.84 | learning rate: 8.503E-05 | global batch size: 256 | lm loss: 2.174879E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.511 | TFLOPs: 18.42 | +31: iteration 23560/ 39672 | consumed samples: 6031360 | consumed tokens: 12352225280 | elapsed time per iteration (s): 0.75 | learning rate: 8.496E-05 | global batch size: 256 | lm loss: 2.165239E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.828 | TFLOPs: 20.62 | +31: iteration 23570/ 39672 | consumed samples: 6033920 | consumed tokens: 12357468160 | elapsed time per iteration (s): 0.77 | learning rate: 8.489E-05 | global batch size: 256 | lm loss: 2.134852E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.361 | TFLOPs: 20.17 | +31: iteration 23580/ 39672 | consumed samples: 6036480 | consumed tokens: 12362711040 | elapsed time per iteration (s): 0.76 | learning rate: 8.482E-05 | global batch size: 256 | lm loss: 2.129847E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.733 | TFLOPs: 20.25 | +31: iteration 23590/ 39672 | consumed samples: 6039040 | consumed tokens: 12367953920 | elapsed time per iteration (s): 0.80 | learning rate: 8.475E-05 | global batch size: 256 | lm loss: 2.113807E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.945 | TFLOPs: 19.36 | +31: iteration 23600/ 39672 | consumed samples: 6041600 | consumed tokens: 12373196800 | elapsed time per iteration (s): 0.76 | learning rate: 8.468E-05 | global batch size: 256 | lm loss: 2.142260E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.720 | TFLOPs: 20.43 | +31: iteration 23610/ 39672 | consumed samples: 6044160 | consumed tokens: 12378439680 | elapsed time per iteration (s): 0.78 | learning rate: 8.461E-05 | global batch size: 256 | lm loss: 2.152857E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.291 | TFLOPs: 19.74 | +31: iteration 23620/ 39672 | consumed samples: 6046720 | consumed tokens: 12383682560 | elapsed time per iteration (s): 0.77 | learning rate: 8.454E-05 | global batch size: 256 | lm loss: 2.164448E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.436 | TFLOPs: 20.05 | +31: iteration 23630/ 39672 | consumed samples: 6049280 | consumed tokens: 12388925440 | elapsed time per iteration (s): 0.84 | learning rate: 8.447E-05 | global batch size: 256 | lm loss: 2.121198E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.100 | TFLOPs: 18.52 | +31: iteration 23640/ 39672 | consumed samples: 6051840 | consumed tokens: 12394168320 | elapsed time per iteration (s): 0.84 | learning rate: 8.440E-05 | global batch size: 256 | lm loss: 2.136504E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.887 | TFLOPs: 18.38 | +31: iteration 23650/ 39672 | consumed samples: 6054400 | consumed tokens: 12399411200 | elapsed time per iteration (s): 0.80 | learning rate: 8.434E-05 | global batch size: 256 | lm loss: 2.105545E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.634 | TFLOPs: 19.34 | +31: iteration 23660/ 39672 | consumed samples: 6056960 | consumed tokens: 12404654080 | elapsed time per iteration (s): 0.78 | learning rate: 8.427E-05 | global batch size: 256 | lm loss: 2.136672E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.152 | TFLOPs: 19.85 | +31: iteration 23670/ 39672 | consumed samples: 6059520 | consumed tokens: 12409896960 | elapsed time per iteration (s): 0.74 | learning rate: 8.420E-05 | global batch size: 256 | lm loss: 2.136939E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.628 | TFLOPs: 20.91 | +31: iteration 23680/ 39672 | consumed samples: 6062080 | consumed tokens: 12415139840 | elapsed time per iteration (s): 0.75 | learning rate: 8.413E-05 | global batch size: 256 | lm loss: 2.129162E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.245 | TFLOPs: 20.70 | +31: iteration 23690/ 39672 | consumed samples: 6064640 | consumed tokens: 12420382720 | elapsed time per iteration (s): 0.74 | learning rate: 8.406E-05 | global batch size: 256 | lm loss: 2.147220E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.999 | TFLOPs: 21.05 | +31: iteration 23700/ 39672 | consumed samples: 6067200 | consumed tokens: 12425625600 | elapsed time per iteration (s): 0.77 | learning rate: 8.399E-05 | global batch size: 256 | lm loss: 2.146794E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.765 | TFLOPs: 20.01 | +31: iteration 23710/ 39672 | consumed samples: 6069760 | consumed tokens: 12430868480 | elapsed time per iteration (s): 0.79 | learning rate: 8.392E-05 | global batch size: 256 | lm loss: 2.137540E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.145 | TFLOPs: 19.55 | +31: iteration 23720/ 39672 | consumed samples: 6072320 | consumed tokens: 12436111360 | elapsed time per iteration (s): 0.79 | learning rate: 8.385E-05 | global batch size: 256 | lm loss: 2.132672E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.392 | TFLOPs: 19.62 | +31: iteration 23730/ 39672 | consumed samples: 6074880 | consumed tokens: 12441354240 | elapsed time per iteration (s): 0.75 | learning rate: 8.378E-05 | global batch size: 256 | lm loss: 2.157092E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.514 | TFLOPs: 20.66 | +31: iteration 23740/ 39672 | consumed samples: 6077440 | consumed tokens: 12446597120 | elapsed time per iteration (s): 0.74 | learning rate: 8.372E-05 | global batch size: 256 | lm loss: 2.102171E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.351 | TFLOPs: 20.89 | +31: iteration 23750/ 39672 | consumed samples: 6080000 | consumed tokens: 12451840000 | elapsed time per iteration (s): 0.81 | learning rate: 8.365E-05 | global batch size: 256 | lm loss: 2.112508E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.891 | TFLOPs: 19.11 | +31: iteration 23760/ 39672 | consumed samples: 6082560 | consumed tokens: 12457082880 | elapsed time per iteration (s): 0.73 | learning rate: 8.358E-05 | global batch size: 256 | lm loss: 2.132842E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.758 | TFLOPs: 21.10 | +31: iteration 23770/ 39672 | consumed samples: 6085120 | consumed tokens: 12462325760 | elapsed time per iteration (s): 0.76 | learning rate: 8.351E-05 | global batch size: 256 | lm loss: 2.155528E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.453 | TFLOPs: 20.29 | +31: iteration 23780/ 39672 | consumed samples: 6087680 | consumed tokens: 12467568640 | elapsed time per iteration (s): 0.77 | learning rate: 8.344E-05 | global batch size: 256 | lm loss: 2.159244E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.631 | TFLOPs: 20.12 | +31: iteration 23790/ 39672 | consumed samples: 6090240 | consumed tokens: 12472811520 | elapsed time per iteration (s): 0.77 | learning rate: 8.337E-05 | global batch size: 256 | lm loss: 2.163782E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.904 | TFLOPs: 20.20 | +31: iteration 23800/ 39672 | consumed samples: 6092800 | consumed tokens: 12478054400 | elapsed time per iteration (s): 0.79 | learning rate: 8.330E-05 | global batch size: 256 | lm loss: 2.139223E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.706 | TFLOPs: 19.58 | +31: iteration 23810/ 39672 | consumed samples: 6095360 | consumed tokens: 12483297280 | elapsed time per iteration (s): 0.79 | learning rate: 8.323E-05 | global batch size: 256 | lm loss: 2.122249E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.218 | TFLOPs: 19.55 | +31: iteration 23820/ 39672 | consumed samples: 6097920 | consumed tokens: 12488540160 | elapsed time per iteration (s): 0.78 | learning rate: 8.317E-05 | global batch size: 256 | lm loss: 2.128662E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.481 | TFLOPs: 19.75 | +31: iteration 23830/ 39672 | consumed samples: 6100480 | consumed tokens: 12493783040 | elapsed time per iteration (s): 0.78 | learning rate: 8.310E-05 | global batch size: 256 | lm loss: 2.136893E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.442 | TFLOPs: 19.87 | +31: iteration 23840/ 39672 | consumed samples: 6103040 | consumed tokens: 12499025920 | elapsed time per iteration (s): 0.80 | learning rate: 8.303E-05 | global batch size: 256 | lm loss: 2.108302E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.623 | TFLOPs: 19.28 | +31: iteration 23850/ 39672 | consumed samples: 6105600 | consumed tokens: 12504268800 | elapsed time per iteration (s): 0.76 | learning rate: 8.296E-05 | global batch size: 256 | lm loss: 2.141018E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.209 | TFLOPs: 20.46 | +31: iteration 23860/ 39672 | consumed samples: 6108160 | consumed tokens: 12509511680 | elapsed time per iteration (s): 0.80 | learning rate: 8.289E-05 | global batch size: 256 | lm loss: 2.114068E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.109 | TFLOPs: 19.31 | +31: iteration 23870/ 39672 | consumed samples: 6110720 | consumed tokens: 12514754560 | elapsed time per iteration (s): 0.78 | learning rate: 8.282E-05 | global batch size: 256 | lm loss: 2.134836E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.694 | TFLOPs: 19.89 | +31: iteration 23880/ 39672 | consumed samples: 6113280 | consumed tokens: 12519997440 | elapsed time per iteration (s): 0.83 | learning rate: 8.275E-05 | global batch size: 256 | lm loss: 2.163354E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.949 | TFLOPs: 18.63 | +31: iteration 23890/ 39672 | consumed samples: 6115840 | consumed tokens: 12525240320 | elapsed time per iteration (s): 0.79 | learning rate: 8.268E-05 | global batch size: 256 | lm loss: 2.142392E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.824 | TFLOPs: 19.71 | +31: iteration 23900/ 39672 | consumed samples: 6118400 | consumed tokens: 12530483200 | elapsed time per iteration (s): 0.78 | learning rate: 8.262E-05 | global batch size: 256 | lm loss: 2.174043E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.384 | TFLOPs: 19.93 | +31: iteration 23910/ 39672 | consumed samples: 6120960 | consumed tokens: 12535726080 | elapsed time per iteration (s): 0.72 | learning rate: 8.255E-05 | global batch size: 256 | lm loss: 2.130365E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.213 | TFLOPs: 21.37 | +31: iteration 23920/ 39672 | consumed samples: 6123520 | consumed tokens: 12540968960 | elapsed time per iteration (s): 0.76 | learning rate: 8.248E-05 | global batch size: 256 | lm loss: 2.117677E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.710 | TFLOPs: 20.25 | +31: iteration 23930/ 39672 | consumed samples: 6126080 | consumed tokens: 12546211840 | elapsed time per iteration (s): 0.81 | learning rate: 8.241E-05 | global batch size: 256 | lm loss: 2.153097E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.692 | TFLOPs: 19.22 | +31: iteration 23940/ 39672 | consumed samples: 6128640 | consumed tokens: 12551454720 | elapsed time per iteration (s): 0.82 | learning rate: 8.234E-05 | global batch size: 256 | lm loss: 2.132180E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.209 | TFLOPs: 18.95 | +31: iteration 23950/ 39672 | consumed samples: 6131200 | consumed tokens: 12556697600 | elapsed time per iteration (s): 0.72 | learning rate: 8.227E-05 | global batch size: 256 | lm loss: 2.132199E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.288 | TFLOPs: 21.37 | +31: iteration 23960/ 39672 | consumed samples: 6133760 | consumed tokens: 12561940480 | elapsed time per iteration (s): 0.73 | learning rate: 8.220E-05 | global batch size: 256 | lm loss: 2.113181E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.168 | TFLOPs: 21.18 | +31: iteration 23970/ 39672 | consumed samples: 6136320 | consumed tokens: 12567183360 | elapsed time per iteration (s): 0.78 | learning rate: 8.214E-05 | global batch size: 256 | lm loss: 2.146567E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.068 | TFLOPs: 19.91 | +31: iteration 23980/ 39672 | consumed samples: 6138880 | consumed tokens: 12572426240 | elapsed time per iteration (s): 0.76 | learning rate: 8.207E-05 | global batch size: 256 | lm loss: 2.145043E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.761 | TFLOPs: 20.25 | +31: iteration 23990/ 39672 | consumed samples: 6141440 | consumed tokens: 12577669120 | elapsed time per iteration (s): 0.81 | learning rate: 8.200E-05 | global batch size: 256 | lm loss: 2.144248E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.005 | TFLOPs: 19.06 | + 0: [2022-11-30 14:31:23,037] [INFO] [logging.py:68:log_dist] [Rank 0] step=24000, skipped=0, lr=[8.19311887570775e-05, 8.19311887570775e-05, 8.19311887570775e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 24000/ 39672 | consumed samples: 6144000 | consumed tokens: 12582912000 | elapsed time per iteration (s): 0.84 | learning rate: 8.193E-05 | global batch size: 256 | lm loss: 2.132784E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.699 | TFLOPs: 18.49 | + 0: steps: 24000 loss: 2.2120 iter time (s): 0.777 samples/sec: 329.366 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 24000 | lm loss value: 2.086237E+00 | lm loss PPL: 8.054550E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 24010/ 39672 | consumed samples: 6146560 | consumed tokens: 12588154880 | elapsed time per iteration (s): 0.83 | learning rate: 8.186E-05 | global batch size: 256 | lm loss: 2.118432E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.743 | TFLOPs: 18.68 | +31: iteration 24020/ 39672 | consumed samples: 6149120 | consumed tokens: 12593397760 | elapsed time per iteration (s): 0.82 | learning rate: 8.179E-05 | global batch size: 256 | lm loss: 2.133526E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.617 | TFLOPs: 18.79 | +31: iteration 24030/ 39672 | consumed samples: 6151680 | consumed tokens: 12598640640 | elapsed time per iteration (s): 0.82 | learning rate: 8.173E-05 | global batch size: 256 | lm loss: 2.152055E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.186 | TFLOPs: 18.83 | +31: iteration 24040/ 39672 | consumed samples: 6154240 | consumed tokens: 12603883520 | elapsed time per iteration (s): 0.81 | learning rate: 8.166E-05 | global batch size: 256 | lm loss: 2.130380E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.153 | TFLOPs: 19.07 | +31: iteration 24050/ 39672 | consumed samples: 6156800 | consumed tokens: 12609126400 | elapsed time per iteration (s): 0.81 | learning rate: 8.159E-05 | global batch size: 256 | lm loss: 2.145630E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.779 | TFLOPs: 19.16 | +31: iteration 24060/ 39672 | consumed samples: 6159360 | consumed tokens: 12614369280 | elapsed time per iteration (s): 0.80 | learning rate: 8.152E-05 | global batch size: 256 | lm loss: 2.142197E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.515 | TFLOPs: 19.27 | +31: iteration 24070/ 39672 | consumed samples: 6161920 | consumed tokens: 12619612160 | elapsed time per iteration (s): 0.84 | learning rate: 8.145E-05 | global batch size: 256 | lm loss: 2.126212E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.863 | TFLOPs: 18.44 | +31: iteration 24080/ 39672 | consumed samples: 6164480 | consumed tokens: 12624855040 | elapsed time per iteration (s): 0.88 | learning rate: 8.138E-05 | global batch size: 256 | lm loss: 2.151633E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 289.417 | TFLOPs: 17.51 | +31: iteration 24090/ 39672 | consumed samples: 6167040 | consumed tokens: 12630097920 | elapsed time per iteration (s): 0.81 | learning rate: 8.132E-05 | global batch size: 256 | lm loss: 2.129687E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.663 | TFLOPs: 19.22 | +31: iteration 24100/ 39672 | consumed samples: 6169600 | consumed tokens: 12635340800 | elapsed time per iteration (s): 0.84 | learning rate: 8.125E-05 | global batch size: 256 | lm loss: 2.107796E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.539 | TFLOPs: 18.48 | +31: iteration 24110/ 39672 | consumed samples: 6172160 | consumed tokens: 12640583680 | elapsed time per iteration (s): 0.82 | learning rate: 8.118E-05 | global batch size: 256 | lm loss: 2.145547E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.595 | TFLOPs: 18.79 | +31: iteration 24120/ 39672 | consumed samples: 6174720 | consumed tokens: 12645826560 | elapsed time per iteration (s): 0.82 | learning rate: 8.111E-05 | global batch size: 256 | lm loss: 2.145096E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.085 | TFLOPs: 18.82 | +31: iteration 24130/ 39672 | consumed samples: 6177280 | consumed tokens: 12651069440 | elapsed time per iteration (s): 0.80 | learning rate: 8.104E-05 | global batch size: 256 | lm loss: 2.141801E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.500 | TFLOPs: 19.27 | +31: iteration 24140/ 39672 | consumed samples: 6179840 | consumed tokens: 12656312320 | elapsed time per iteration (s): 0.86 | learning rate: 8.098E-05 | global batch size: 256 | lm loss: 2.109970E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.691 | TFLOPs: 18.01 | +31: iteration 24150/ 39672 | consumed samples: 6182400 | consumed tokens: 12661555200 | elapsed time per iteration (s): 0.85 | learning rate: 8.091E-05 | global batch size: 256 | lm loss: 2.138035E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.444 | TFLOPs: 18.24 | +31: iteration 24160/ 39672 | consumed samples: 6184960 | consumed tokens: 12666798080 | elapsed time per iteration (s): 0.83 | learning rate: 8.084E-05 | global batch size: 256 | lm loss: 2.144556E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.266 | TFLOPs: 18.77 | +31: iteration 24170/ 39672 | consumed samples: 6187520 | consumed tokens: 12672040960 | elapsed time per iteration (s): 0.84 | learning rate: 8.077E-05 | global batch size: 256 | lm loss: 2.131373E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.466 | TFLOPs: 18.42 | +31: iteration 24180/ 39672 | consumed samples: 6190080 | consumed tokens: 12677283840 | elapsed time per iteration (s): 0.83 | learning rate: 8.070E-05 | global batch size: 256 | lm loss: 2.139991E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.812 | TFLOPs: 18.62 | +31: iteration 24190/ 39672 | consumed samples: 6192640 | consumed tokens: 12682526720 | elapsed time per iteration (s): 0.84 | learning rate: 8.063E-05 | global batch size: 256 | lm loss: 2.129305E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.710 | TFLOPs: 18.37 | +31: iteration 24200/ 39672 | consumed samples: 6195200 | consumed tokens: 12687769600 | elapsed time per iteration (s): 0.87 | learning rate: 8.057E-05 | global batch size: 256 | lm loss: 2.149313E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.584 | TFLOPs: 17.88 | +31: iteration 24210/ 39672 | consumed samples: 6197760 | consumed tokens: 12693012480 | elapsed time per iteration (s): 0.73 | learning rate: 8.050E-05 | global batch size: 256 | lm loss: 2.133653E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.828 | TFLOPs: 21.28 | +31: iteration 24220/ 39672 | consumed samples: 6200320 | consumed tokens: 12698255360 | elapsed time per iteration (s): 0.76 | learning rate: 8.043E-05 | global batch size: 256 | lm loss: 2.108971E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.831 | TFLOPs: 20.26 | +31: iteration 24230/ 39672 | consumed samples: 6202880 | consumed tokens: 12703498240 | elapsed time per iteration (s): 0.75 | learning rate: 8.036E-05 | global batch size: 256 | lm loss: 2.125195E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.172 | TFLOPs: 20.70 | +31: iteration 24240/ 39672 | consumed samples: 6205440 | consumed tokens: 12708741120 | elapsed time per iteration (s): 0.80 | learning rate: 8.029E-05 | global batch size: 256 | lm loss: 2.134679E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.711 | TFLOPs: 19.40 | +31: iteration 24250/ 39672 | consumed samples: 6208000 | consumed tokens: 12713984000 | elapsed time per iteration (s): 0.76 | learning rate: 8.023E-05 | global batch size: 256 | lm loss: 2.139800E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.965 | TFLOPs: 20.39 | +31: iteration 24260/ 39672 | consumed samples: 6210560 | consumed tokens: 12719226880 | elapsed time per iteration (s): 0.79 | learning rate: 8.016E-05 | global batch size: 256 | lm loss: 2.129629E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.370 | TFLOPs: 19.50 | +31: iteration 24270/ 39672 | consumed samples: 6213120 | consumed tokens: 12724469760 | elapsed time per iteration (s): 0.76 | learning rate: 8.009E-05 | global batch size: 256 | lm loss: 2.150548E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.248 | TFLOPs: 20.28 | +31: iteration 24280/ 39672 | consumed samples: 6215680 | consumed tokens: 12729712640 | elapsed time per iteration (s): 0.77 | learning rate: 8.002E-05 | global batch size: 256 | lm loss: 2.138853E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.127 | TFLOPs: 20.03 | +31: iteration 24290/ 39672 | consumed samples: 6218240 | consumed tokens: 12734955520 | elapsed time per iteration (s): 0.81 | learning rate: 7.996E-05 | global batch size: 256 | lm loss: 2.104237E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.650 | TFLOPs: 19.16 | +31: iteration 24300/ 39672 | consumed samples: 6220800 | consumed tokens: 12740198400 | elapsed time per iteration (s): 0.83 | learning rate: 7.989E-05 | global batch size: 256 | lm loss: 2.125674E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.143 | TFLOPs: 18.70 | +31: iteration 24310/ 39672 | consumed samples: 6223360 | consumed tokens: 12745441280 | elapsed time per iteration (s): 0.83 | learning rate: 7.982E-05 | global batch size: 256 | lm loss: 2.121255E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.877 | TFLOPs: 18.75 | +31: iteration 24320/ 39672 | consumed samples: 6225920 | consumed tokens: 12750684160 | elapsed time per iteration (s): 0.78 | learning rate: 7.975E-05 | global batch size: 256 | lm loss: 2.133800E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.876 | TFLOPs: 19.84 | +31: iteration 24330/ 39672 | consumed samples: 6228480 | consumed tokens: 12755927040 | elapsed time per iteration (s): 0.81 | learning rate: 7.968E-05 | global batch size: 256 | lm loss: 2.132231E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.755 | TFLOPs: 19.04 | +31: iteration 24340/ 39672 | consumed samples: 6231040 | consumed tokens: 12761169920 | elapsed time per iteration (s): 0.76 | learning rate: 7.962E-05 | global batch size: 256 | lm loss: 2.142232E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.458 | TFLOPs: 20.42 | +31: iteration 24350/ 39672 | consumed samples: 6233600 | consumed tokens: 12766412800 | elapsed time per iteration (s): 0.75 | learning rate: 7.955E-05 | global batch size: 256 | lm loss: 2.137321E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.801 | TFLOPs: 20.56 | +31: iteration 24360/ 39672 | consumed samples: 6236160 | consumed tokens: 12771655680 | elapsed time per iteration (s): 0.82 | learning rate: 7.948E-05 | global batch size: 256 | lm loss: 2.127546E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.275 | TFLOPs: 18.95 | +31: iteration 24370/ 39672 | consumed samples: 6238720 | consumed tokens: 12776898560 | elapsed time per iteration (s): 0.77 | learning rate: 7.941E-05 | global batch size: 256 | lm loss: 2.139287E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.269 | TFLOPs: 20.22 | +31: iteration 24380/ 39672 | consumed samples: 6241280 | consumed tokens: 12782141440 | elapsed time per iteration (s): 0.77 | learning rate: 7.935E-05 | global batch size: 256 | lm loss: 2.103201E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.096 | TFLOPs: 20.03 | +31: iteration 24390/ 39672 | consumed samples: 6243840 | consumed tokens: 12787384320 | elapsed time per iteration (s): 0.72 | learning rate: 7.928E-05 | global batch size: 256 | lm loss: 2.109914E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.075 | TFLOPs: 21.42 | +31: iteration 24400/ 39672 | consumed samples: 6246400 | consumed tokens: 12792627200 | elapsed time per iteration (s): 0.82 | learning rate: 7.921E-05 | global batch size: 256 | lm loss: 2.147874E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.887 | TFLOPs: 18.99 | +31: iteration 24410/ 39672 | consumed samples: 6248960 | consumed tokens: 12797870080 | elapsed time per iteration (s): 0.75 | learning rate: 7.914E-05 | global batch size: 256 | lm loss: 2.139094E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.316 | TFLOPs: 20.65 | +31: iteration 24420/ 39672 | consumed samples: 6251520 | consumed tokens: 12803112960 | elapsed time per iteration (s): 0.79 | learning rate: 7.907E-05 | global batch size: 256 | lm loss: 2.148859E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.256 | TFLOPs: 19.68 | +31: iteration 24430/ 39672 | consumed samples: 6254080 | consumed tokens: 12808355840 | elapsed time per iteration (s): 0.84 | learning rate: 7.901E-05 | global batch size: 256 | lm loss: 2.148824E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.428 | TFLOPs: 18.48 | +31: iteration 24440/ 39672 | consumed samples: 6256640 | consumed tokens: 12813598720 | elapsed time per iteration (s): 0.81 | learning rate: 7.894E-05 | global batch size: 256 | lm loss: 2.137153E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.131 | TFLOPs: 19.13 | +31: iteration 24450/ 39672 | consumed samples: 6259200 | consumed tokens: 12818841600 | elapsed time per iteration (s): 0.78 | learning rate: 7.887E-05 | global batch size: 256 | lm loss: 2.118208E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.373 | TFLOPs: 19.74 | +31: iteration 24460/ 39672 | consumed samples: 6261760 | consumed tokens: 12824084480 | elapsed time per iteration (s): 0.75 | learning rate: 7.880E-05 | global batch size: 256 | lm loss: 2.154083E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.387 | TFLOPs: 20.53 | +31: iteration 24470/ 39672 | consumed samples: 6264320 | consumed tokens: 12829327360 | elapsed time per iteration (s): 0.79 | learning rate: 7.874E-05 | global batch size: 256 | lm loss: 2.129368E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.398 | TFLOPs: 19.63 | +31: iteration 24480/ 39672 | consumed samples: 6266880 | consumed tokens: 12834570240 | elapsed time per iteration (s): 0.86 | learning rate: 7.867E-05 | global batch size: 256 | lm loss: 2.147611E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.068 | TFLOPs: 18.09 | +31: iteration 24490/ 39672 | consumed samples: 6269440 | consumed tokens: 12839813120 | elapsed time per iteration (s): 0.81 | learning rate: 7.860E-05 | global batch size: 256 | lm loss: 2.138477E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.711 | TFLOPs: 19.22 | +31: iteration 24500/ 39672 | consumed samples: 6272000 | consumed tokens: 12845056000 | elapsed time per iteration (s): 0.79 | learning rate: 7.853E-05 | global batch size: 256 | lm loss: 2.143655E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.270 | TFLOPs: 19.50 | +31: iteration 24510/ 39672 | consumed samples: 6274560 | consumed tokens: 12850298880 | elapsed time per iteration (s): 0.76 | learning rate: 7.847E-05 | global batch size: 256 | lm loss: 2.155876E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.974 | TFLOPs: 20.39 | +31: iteration 24520/ 39672 | consumed samples: 6277120 | consumed tokens: 12855541760 | elapsed time per iteration (s): 0.77 | learning rate: 7.840E-05 | global batch size: 256 | lm loss: 2.171742E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.796 | TFLOPs: 20.13 | +31: iteration 24530/ 39672 | consumed samples: 6279680 | consumed tokens: 12860784640 | elapsed time per iteration (s): 0.73 | learning rate: 7.833E-05 | global batch size: 256 | lm loss: 2.135582E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.589 | TFLOPs: 21.09 | +31: iteration 24540/ 39672 | consumed samples: 6282240 | consumed tokens: 12866027520 | elapsed time per iteration (s): 0.75 | learning rate: 7.827E-05 | global batch size: 256 | lm loss: 2.155859E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.769 | TFLOPs: 20.68 | +31: iteration 24550/ 39672 | consumed samples: 6284800 | consumed tokens: 12871270400 | elapsed time per iteration (s): 0.77 | learning rate: 7.820E-05 | global batch size: 256 | lm loss: 2.135706E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.595 | TFLOPs: 20.12 | +31: iteration 24560/ 39672 | consumed samples: 6287360 | consumed tokens: 12876513280 | elapsed time per iteration (s): 0.86 | learning rate: 7.813E-05 | global batch size: 256 | lm loss: 2.143167E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.541 | TFLOPs: 18.06 | +31: iteration 24570/ 39672 | consumed samples: 6289920 | consumed tokens: 12881756160 | elapsed time per iteration (s): 0.76 | learning rate: 7.806E-05 | global batch size: 256 | lm loss: 2.164343E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.674 | TFLOPs: 20.25 | +31: iteration 24580/ 39672 | consumed samples: 6292480 | consumed tokens: 12886999040 | elapsed time per iteration (s): 0.77 | learning rate: 7.800E-05 | global batch size: 256 | lm loss: 2.154723E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.896 | TFLOPs: 20.08 | +31: iteration 24590/ 39672 | consumed samples: 6295040 | consumed tokens: 12892241920 | elapsed time per iteration (s): 0.77 | learning rate: 7.793E-05 | global batch size: 256 | lm loss: 2.092320E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.703 | TFLOPs: 20.01 | +31: iteration 24600/ 39672 | consumed samples: 6297600 | consumed tokens: 12897484800 | elapsed time per iteration (s): 0.98 | learning rate: 7.786E-05 | global batch size: 256 | lm loss: 2.129848E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 259.979 | TFLOPs: 15.73 | +31: iteration 24610/ 39672 | consumed samples: 6300160 | consumed tokens: 12902727680 | elapsed time per iteration (s): 0.95 | learning rate: 7.779E-05 | global batch size: 256 | lm loss: 2.140209E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 270.787 | TFLOPs: 16.38 | +31: iteration 24620/ 39672 | consumed samples: 6302720 | consumed tokens: 12907970560 | elapsed time per iteration (s): 0.86 | learning rate: 7.773E-05 | global batch size: 256 | lm loss: 2.172576E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.377 | TFLOPs: 17.99 | +31: iteration 24630/ 39672 | consumed samples: 6305280 | consumed tokens: 12913213440 | elapsed time per iteration (s): 0.76 | learning rate: 7.766E-05 | global batch size: 256 | lm loss: 2.132780E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.474 | TFLOPs: 20.36 | +31: iteration 24640/ 39672 | consumed samples: 6307840 | consumed tokens: 12918456320 | elapsed time per iteration (s): 0.78 | learning rate: 7.759E-05 | global batch size: 256 | lm loss: 2.158125E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.931 | TFLOPs: 19.90 | +31: iteration 24650/ 39672 | consumed samples: 6310400 | consumed tokens: 12923699200 | elapsed time per iteration (s): 0.74 | learning rate: 7.753E-05 | global batch size: 256 | lm loss: 2.147071E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.648 | TFLOPs: 20.85 | +31: iteration 24660/ 39672 | consumed samples: 6312960 | consumed tokens: 12928942080 | elapsed time per iteration (s): 0.75 | learning rate: 7.746E-05 | global batch size: 256 | lm loss: 2.141998E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.611 | TFLOPs: 20.55 | +31: iteration 24670/ 39672 | consumed samples: 6315520 | consumed tokens: 12934184960 | elapsed time per iteration (s): 0.72 | learning rate: 7.739E-05 | global batch size: 256 | lm loss: 2.144862E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.065 | TFLOPs: 21.60 | +31: iteration 24680/ 39672 | consumed samples: 6318080 | consumed tokens: 12939427840 | elapsed time per iteration (s): 0.78 | learning rate: 7.732E-05 | global batch size: 256 | lm loss: 2.128564E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.658 | TFLOPs: 19.94 | +31: iteration 24690/ 39672 | consumed samples: 6320640 | consumed tokens: 12944670720 | elapsed time per iteration (s): 0.76 | learning rate: 7.726E-05 | global batch size: 256 | lm loss: 2.164184E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.715 | TFLOPs: 20.37 | +31: iteration 24700/ 39672 | consumed samples: 6323200 | consumed tokens: 12949913600 | elapsed time per iteration (s): 0.80 | learning rate: 7.719E-05 | global batch size: 256 | lm loss: 2.155251E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.300 | TFLOPs: 19.32 | +31: iteration 24710/ 39672 | consumed samples: 6325760 | consumed tokens: 12955156480 | elapsed time per iteration (s): 0.98 | learning rate: 7.712E-05 | global batch size: 256 | lm loss: 2.084150E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 260.095 | TFLOPs: 15.74 | +31: iteration 24720/ 39672 | consumed samples: 6328320 | consumed tokens: 12960399360 | elapsed time per iteration (s): 0.81 | learning rate: 7.706E-05 | global batch size: 256 | lm loss: 2.134778E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.003 | TFLOPs: 19.24 | +31: iteration 24730/ 39672 | consumed samples: 6330880 | consumed tokens: 12965642240 | elapsed time per iteration (s): 0.78 | learning rate: 7.699E-05 | global batch size: 256 | lm loss: 2.113256E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.624 | TFLOPs: 19.76 | +31: iteration 24740/ 39672 | consumed samples: 6333440 | consumed tokens: 12970885120 | elapsed time per iteration (s): 0.81 | learning rate: 7.692E-05 | global batch size: 256 | lm loss: 2.129738E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.231 | TFLOPs: 19.19 | +31: iteration 24750/ 39672 | consumed samples: 6336000 | consumed tokens: 12976128000 | elapsed time per iteration (s): 0.79 | learning rate: 7.685E-05 | global batch size: 256 | lm loss: 2.113115E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.911 | TFLOPs: 19.72 | +31: iteration 24760/ 39672 | consumed samples: 6338560 | consumed tokens: 12981370880 | elapsed time per iteration (s): 0.75 | learning rate: 7.679E-05 | global batch size: 256 | lm loss: 2.113774E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.698 | TFLOPs: 20.55 | +31: iteration 24770/ 39672 | consumed samples: 6341120 | consumed tokens: 12986613760 | elapsed time per iteration (s): 0.82 | learning rate: 7.672E-05 | global batch size: 256 | lm loss: 2.142161E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.573 | TFLOPs: 18.85 | +31: iteration 24780/ 39672 | consumed samples: 6343680 | consumed tokens: 12991856640 | elapsed time per iteration (s): 0.78 | learning rate: 7.665E-05 | global batch size: 256 | lm loss: 2.132438E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.348 | TFLOPs: 19.80 | +31: iteration 24790/ 39672 | consumed samples: 6346240 | consumed tokens: 12997099520 | elapsed time per iteration (s): 0.82 | learning rate: 7.659E-05 | global batch size: 256 | lm loss: 2.135290E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.968 | TFLOPs: 18.87 | +31: iteration 24800/ 39672 | consumed samples: 6348800 | consumed tokens: 13002342400 | elapsed time per iteration (s): 0.75 | learning rate: 7.652E-05 | global batch size: 256 | lm loss: 2.131597E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.566 | TFLOPs: 20.54 | +31: iteration 24810/ 39672 | consumed samples: 6351360 | consumed tokens: 13007585280 | elapsed time per iteration (s): 0.74 | learning rate: 7.645E-05 | global batch size: 256 | lm loss: 2.152666E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.624 | TFLOPs: 21.03 | +31: iteration 24820/ 39672 | consumed samples: 6353920 | consumed tokens: 13012828160 | elapsed time per iteration (s): 0.76 | learning rate: 7.639E-05 | global batch size: 256 | lm loss: 2.141319E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.554 | TFLOPs: 20.30 | +31: iteration 24830/ 39672 | consumed samples: 6356480 | consumed tokens: 13018071040 | elapsed time per iteration (s): 0.76 | learning rate: 7.632E-05 | global batch size: 256 | lm loss: 2.143398E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.851 | TFLOPs: 20.50 | +31: iteration 24840/ 39672 | consumed samples: 6359040 | consumed tokens: 13023313920 | elapsed time per iteration (s): 0.75 | learning rate: 7.625E-05 | global batch size: 256 | lm loss: 2.114556E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.285 | TFLOPs: 20.77 | +31: iteration 24850/ 39672 | consumed samples: 6361600 | consumed tokens: 13028556800 | elapsed time per iteration (s): 0.75 | learning rate: 7.619E-05 | global batch size: 256 | lm loss: 2.141113E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.656 | TFLOPs: 20.73 | +31: iteration 24860/ 39672 | consumed samples: 6364160 | consumed tokens: 13033799680 | elapsed time per iteration (s): 0.77 | learning rate: 7.612E-05 | global batch size: 256 | lm loss: 2.091271E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.313 | TFLOPs: 20.16 | +31: iteration 24870/ 39672 | consumed samples: 6366720 | consumed tokens: 13039042560 | elapsed time per iteration (s): 0.78 | learning rate: 7.605E-05 | global batch size: 256 | lm loss: 2.131952E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.384 | TFLOPs: 19.81 | +31: iteration 24880/ 39672 | consumed samples: 6369280 | consumed tokens: 13044285440 | elapsed time per iteration (s): 0.82 | learning rate: 7.599E-05 | global batch size: 256 | lm loss: 2.120613E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.956 | TFLOPs: 18.99 | +31: iteration 24890/ 39672 | consumed samples: 6371840 | consumed tokens: 13049528320 | elapsed time per iteration (s): 0.79 | learning rate: 7.592E-05 | global batch size: 256 | lm loss: 2.131589E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.074 | TFLOPs: 19.73 | +31: iteration 24900/ 39672 | consumed samples: 6374400 | consumed tokens: 13054771200 | elapsed time per iteration (s): 0.77 | learning rate: 7.585E-05 | global batch size: 256 | lm loss: 2.109571E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.975 | TFLOPs: 20.14 | +31: iteration 24910/ 39672 | consumed samples: 6376960 | consumed tokens: 13060014080 | elapsed time per iteration (s): 0.72 | learning rate: 7.579E-05 | global batch size: 256 | lm loss: 2.109561E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.153 | TFLOPs: 21.49 | +31: iteration 24920/ 39672 | consumed samples: 6379520 | consumed tokens: 13065256960 | elapsed time per iteration (s): 0.77 | learning rate: 7.572E-05 | global batch size: 256 | lm loss: 2.126898E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.124 | TFLOPs: 20.03 | +31: iteration 24930/ 39672 | consumed samples: 6382080 | consumed tokens: 13070499840 | elapsed time per iteration (s): 0.79 | learning rate: 7.565E-05 | global batch size: 256 | lm loss: 2.127817E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.707 | TFLOPs: 19.70 | +31: iteration 24940/ 39672 | consumed samples: 6384640 | consumed tokens: 13075742720 | elapsed time per iteration (s): 0.74 | learning rate: 7.559E-05 | global batch size: 256 | lm loss: 2.119614E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.909 | TFLOPs: 20.93 | +31: iteration 24950/ 39672 | consumed samples: 6387200 | consumed tokens: 13080985600 | elapsed time per iteration (s): 0.83 | learning rate: 7.552E-05 | global batch size: 256 | lm loss: 2.129450E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.163 | TFLOPs: 18.58 | +31: iteration 24960/ 39672 | consumed samples: 6389760 | consumed tokens: 13086228480 | elapsed time per iteration (s): 0.81 | learning rate: 7.545E-05 | global batch size: 256 | lm loss: 2.117397E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.106 | TFLOPs: 19.06 | +31: iteration 24970/ 39672 | consumed samples: 6392320 | consumed tokens: 13091471360 | elapsed time per iteration (s): 0.84 | learning rate: 7.539E-05 | global batch size: 256 | lm loss: 2.110170E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.278 | TFLOPs: 18.47 | +31: iteration 24980/ 39672 | consumed samples: 6394880 | consumed tokens: 13096714240 | elapsed time per iteration (s): 0.78 | learning rate: 7.532E-05 | global batch size: 256 | lm loss: 2.109841E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.741 | TFLOPs: 19.83 | +31: iteration 24990/ 39672 | consumed samples: 6397440 | consumed tokens: 13101957120 | elapsed time per iteration (s): 0.74 | learning rate: 7.525E-05 | global batch size: 256 | lm loss: 2.127884E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.626 | TFLOPs: 20.97 | +31: iteration 25000/ 39672 | consumed samples: 6400000 | consumed tokens: 13107200000 | elapsed time per iteration (s): 0.80 | learning rate: 7.519E-05 | global batch size: 256 | lm loss: 2.128089E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.539 | TFLOPs: 19.45 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 25000 | lm loss value: 2.088991E+00 | lm loss PPL: 8.076759E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 25010/ 39672 | consumed samples: 6402560 | consumed tokens: 13112442880 | elapsed time per iteration (s): 0.75 | learning rate: 7.512E-05 | global batch size: 256 | lm loss: 2.115845E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.830 | TFLOPs: 20.62 | +31: iteration 25020/ 39672 | consumed samples: 6405120 | consumed tokens: 13117685760 | elapsed time per iteration (s): 0.77 | learning rate: 7.506E-05 | global batch size: 256 | lm loss: 2.121819E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.806 | TFLOPs: 20.13 | +31: iteration 25030/ 39672 | consumed samples: 6407680 | consumed tokens: 13122928640 | elapsed time per iteration (s): 0.82 | learning rate: 7.499E-05 | global batch size: 256 | lm loss: 2.125426E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.545 | TFLOPs: 18.91 | +31: iteration 25040/ 39672 | consumed samples: 6410240 | consumed tokens: 13128171520 | elapsed time per iteration (s): 0.82 | learning rate: 7.492E-05 | global batch size: 256 | lm loss: 2.144327E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.743 | TFLOPs: 18.86 | +31: iteration 25050/ 39672 | consumed samples: 6412800 | consumed tokens: 13133414400 | elapsed time per iteration (s): 0.82 | learning rate: 7.486E-05 | global batch size: 256 | lm loss: 2.148361E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.646 | TFLOPs: 18.91 | +31: iteration 25060/ 39672 | consumed samples: 6415360 | consumed tokens: 13138657280 | elapsed time per iteration (s): 0.80 | learning rate: 7.479E-05 | global batch size: 256 | lm loss: 2.135711E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.617 | TFLOPs: 19.34 | +31: iteration 25070/ 39672 | consumed samples: 6417920 | consumed tokens: 13143900160 | elapsed time per iteration (s): 0.79 | learning rate: 7.472E-05 | global batch size: 256 | lm loss: 2.123983E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.442 | TFLOPs: 19.51 | +31: iteration 25080/ 39672 | consumed samples: 6420480 | consumed tokens: 13149143040 | elapsed time per iteration (s): 0.73 | learning rate: 7.466E-05 | global batch size: 256 | lm loss: 2.142851E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.855 | TFLOPs: 21.10 | +31: iteration 25090/ 39672 | consumed samples: 6423040 | consumed tokens: 13154385920 | elapsed time per iteration (s): 0.75 | learning rate: 7.459E-05 | global batch size: 256 | lm loss: 2.130670E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.886 | TFLOPs: 20.62 | +31: iteration 25100/ 39672 | consumed samples: 6425600 | consumed tokens: 13159628800 | elapsed time per iteration (s): 0.81 | learning rate: 7.453E-05 | global batch size: 256 | lm loss: 2.135687E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.883 | TFLOPs: 19.17 | +31: iteration 25110/ 39672 | consumed samples: 6428160 | consumed tokens: 13164871680 | elapsed time per iteration (s): 0.76 | learning rate: 7.446E-05 | global batch size: 256 | lm loss: 2.125079E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.704 | TFLOPs: 20.43 | +31: iteration 25120/ 39672 | consumed samples: 6430720 | consumed tokens: 13170114560 | elapsed time per iteration (s): 0.75 | learning rate: 7.439E-05 | global batch size: 256 | lm loss: 2.115857E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.798 | TFLOPs: 20.56 | +31: iteration 25130/ 39672 | consumed samples: 6433280 | consumed tokens: 13175357440 | elapsed time per iteration (s): 0.73 | learning rate: 7.433E-05 | global batch size: 256 | lm loss: 2.126824E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.775 | TFLOPs: 21.22 | +31: iteration 25140/ 39672 | consumed samples: 6435840 | consumed tokens: 13180600320 | elapsed time per iteration (s): 0.75 | learning rate: 7.426E-05 | global batch size: 256 | lm loss: 2.124949E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.599 | TFLOPs: 20.54 | +31: iteration 25150/ 39672 | consumed samples: 6438400 | consumed tokens: 13185843200 | elapsed time per iteration (s): 0.78 | learning rate: 7.420E-05 | global batch size: 256 | lm loss: 2.142427E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.074 | TFLOPs: 19.91 | +31: iteration 25160/ 39672 | consumed samples: 6440960 | consumed tokens: 13191086080 | elapsed time per iteration (s): 1.00 | learning rate: 7.413E-05 | global batch size: 256 | lm loss: 2.147144E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 255.890 | TFLOPs: 15.48 | +31: iteration 25170/ 39672 | consumed samples: 6443520 | consumed tokens: 13196328960 | elapsed time per iteration (s): 0.88 | learning rate: 7.406E-05 | global batch size: 256 | lm loss: 2.132814E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 291.633 | TFLOPs: 17.64 | +31: iteration 25180/ 39672 | consumed samples: 6446080 | consumed tokens: 13201571840 | elapsed time per iteration (s): 0.78 | learning rate: 7.400E-05 | global batch size: 256 | lm loss: 2.123647E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.797 | TFLOPs: 19.95 | +31: iteration 25190/ 39672 | consumed samples: 6448640 | consumed tokens: 13206814720 | elapsed time per iteration (s): 0.78 | learning rate: 7.393E-05 | global batch size: 256 | lm loss: 2.143522E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.003 | TFLOPs: 19.78 | +31: iteration 25200/ 39672 | consumed samples: 6451200 | consumed tokens: 13212057600 | elapsed time per iteration (s): 0.85 | learning rate: 7.387E-05 | global batch size: 256 | lm loss: 2.131258E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.504 | TFLOPs: 18.30 | +31: iteration 25210/ 39672 | consumed samples: 6453760 | consumed tokens: 13217300480 | elapsed time per iteration (s): 0.84 | learning rate: 7.380E-05 | global batch size: 256 | lm loss: 2.141529E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.758 | TFLOPs: 18.50 | +31: iteration 25220/ 39672 | consumed samples: 6456320 | consumed tokens: 13222543360 | elapsed time per iteration (s): 0.81 | learning rate: 7.373E-05 | global batch size: 256 | lm loss: 2.144788E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.405 | TFLOPs: 19.14 | +31: iteration 25230/ 39672 | consumed samples: 6458880 | consumed tokens: 13227786240 | elapsed time per iteration (s): 0.82 | learning rate: 7.367E-05 | global batch size: 256 | lm loss: 2.119150E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.145 | TFLOPs: 18.82 | +31: iteration 25240/ 39672 | consumed samples: 6461440 | consumed tokens: 13233029120 | elapsed time per iteration (s): 0.82 | learning rate: 7.360E-05 | global batch size: 256 | lm loss: 2.132914E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.153 | TFLOPs: 18.94 | +31: iteration 25250/ 39672 | consumed samples: 6464000 | consumed tokens: 13238272000 | elapsed time per iteration (s): 0.83 | learning rate: 7.354E-05 | global batch size: 256 | lm loss: 2.119621E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.903 | TFLOPs: 18.69 | +31: iteration 25260/ 39672 | consumed samples: 6466560 | consumed tokens: 13243514880 | elapsed time per iteration (s): 0.79 | learning rate: 7.347E-05 | global batch size: 256 | lm loss: 2.125557E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.773 | TFLOPs: 19.65 | +31: iteration 25270/ 39672 | consumed samples: 6469120 | consumed tokens: 13248757760 | elapsed time per iteration (s): 0.83 | learning rate: 7.340E-05 | global batch size: 256 | lm loss: 2.144792E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.669 | TFLOPs: 18.73 | +31: iteration 25280/ 39672 | consumed samples: 6471680 | consumed tokens: 13254000640 | elapsed time per iteration (s): 0.79 | learning rate: 7.334E-05 | global batch size: 256 | lm loss: 2.152743E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.549 | TFLOPs: 19.57 | +31: iteration 25290/ 39672 | consumed samples: 6474240 | consumed tokens: 13259243520 | elapsed time per iteration (s): 0.83 | learning rate: 7.327E-05 | global batch size: 256 | lm loss: 2.078522E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.155 | TFLOPs: 18.58 | +31: iteration 25300/ 39672 | consumed samples: 6476800 | consumed tokens: 13264486400 | elapsed time per iteration (s): 0.82 | learning rate: 7.321E-05 | global batch size: 256 | lm loss: 2.139551E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.469 | TFLOPs: 18.84 | +31: iteration 25310/ 39672 | consumed samples: 6479360 | consumed tokens: 13269729280 | elapsed time per iteration (s): 0.81 | learning rate: 7.314E-05 | global batch size: 256 | lm loss: 2.119840E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.535 | TFLOPs: 19.15 | +31: iteration 25320/ 39672 | consumed samples: 6481920 | consumed tokens: 13274972160 | elapsed time per iteration (s): 0.81 | learning rate: 7.308E-05 | global batch size: 256 | lm loss: 2.127236E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.383 | TFLOPs: 19.20 | +31: iteration 25330/ 39672 | consumed samples: 6484480 | consumed tokens: 13280215040 | elapsed time per iteration (s): 0.81 | learning rate: 7.301E-05 | global batch size: 256 | lm loss: 2.127846E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.648 | TFLOPs: 19.10 | +31: iteration 25340/ 39672 | consumed samples: 6487040 | consumed tokens: 13285457920 | elapsed time per iteration (s): 0.82 | learning rate: 7.294E-05 | global batch size: 256 | lm loss: 2.132491E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.602 | TFLOPs: 18.91 | +31: iteration 25350/ 39672 | consumed samples: 6489600 | consumed tokens: 13290700800 | elapsed time per iteration (s): 0.83 | learning rate: 7.288E-05 | global batch size: 256 | lm loss: 2.121560E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.487 | TFLOPs: 18.60 | +31: iteration 25360/ 39672 | consumed samples: 6492160 | consumed tokens: 13295943680 | elapsed time per iteration (s): 0.85 | learning rate: 7.281E-05 | global batch size: 256 | lm loss: 2.120433E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.897 | TFLOPs: 18.26 | +31: iteration 25370/ 39672 | consumed samples: 6494720 | consumed tokens: 13301186560 | elapsed time per iteration (s): 0.85 | learning rate: 7.275E-05 | global batch size: 256 | lm loss: 2.112257E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.220 | TFLOPs: 18.22 | +31: iteration 25380/ 39672 | consumed samples: 6497280 | consumed tokens: 13306429440 | elapsed time per iteration (s): 0.84 | learning rate: 7.268E-05 | global batch size: 256 | lm loss: 2.141741E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.487 | TFLOPs: 18.54 | +31: iteration 25390/ 39672 | consumed samples: 6499840 | consumed tokens: 13311672320 | elapsed time per iteration (s): 0.82 | learning rate: 7.262E-05 | global batch size: 256 | lm loss: 2.160403E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.663 | TFLOPs: 18.98 | +31: iteration 25400/ 39672 | consumed samples: 6502400 | consumed tokens: 13316915200 | elapsed time per iteration (s): 0.84 | learning rate: 7.255E-05 | global batch size: 256 | lm loss: 2.139146E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.108 | TFLOPs: 18.34 | +31: iteration 25410/ 39672 | consumed samples: 6504960 | consumed tokens: 13322158080 | elapsed time per iteration (s): 0.81 | learning rate: 7.249E-05 | global batch size: 256 | lm loss: 2.100014E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.441 | TFLOPs: 19.14 | +31: iteration 25420/ 39672 | consumed samples: 6507520 | consumed tokens: 13327400960 | elapsed time per iteration (s): 0.77 | learning rate: 7.242E-05 | global batch size: 256 | lm loss: 2.113150E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.106 | TFLOPs: 20.15 | +31: iteration 25430/ 39672 | consumed samples: 6510080 | consumed tokens: 13332643840 | elapsed time per iteration (s): 0.79 | learning rate: 7.235E-05 | global batch size: 256 | lm loss: 2.149250E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.042 | TFLOPs: 19.48 | +31: iteration 25440/ 39672 | consumed samples: 6512640 | consumed tokens: 13337886720 | elapsed time per iteration (s): 0.79 | learning rate: 7.229E-05 | global batch size: 256 | lm loss: 2.117161E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.546 | TFLOPs: 19.63 | +31: iteration 25450/ 39672 | consumed samples: 6515200 | consumed tokens: 13343129600 | elapsed time per iteration (s): 0.76 | learning rate: 7.222E-05 | global batch size: 256 | lm loss: 2.123317E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.285 | TFLOPs: 20.40 | +31: iteration 25460/ 39672 | consumed samples: 6517760 | consumed tokens: 13348372480 | elapsed time per iteration (s): 0.79 | learning rate: 7.216E-05 | global batch size: 256 | lm loss: 2.149669E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.005 | TFLOPs: 19.66 | +31: iteration 25470/ 39672 | consumed samples: 6520320 | consumed tokens: 13353615360 | elapsed time per iteration (s): 0.78 | learning rate: 7.209E-05 | global batch size: 256 | lm loss: 2.135642E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.479 | TFLOPs: 19.93 | +31: iteration 25480/ 39672 | consumed samples: 6522880 | consumed tokens: 13358858240 | elapsed time per iteration (s): 0.80 | learning rate: 7.203E-05 | global batch size: 256 | lm loss: 2.134468E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.538 | TFLOPs: 19.39 | +31: iteration 25490/ 39672 | consumed samples: 6525440 | consumed tokens: 13364101120 | elapsed time per iteration (s): 0.78 | learning rate: 7.196E-05 | global batch size: 256 | lm loss: 2.104399E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.005 | TFLOPs: 19.96 | +31: iteration 25500/ 39672 | consumed samples: 6528000 | consumed tokens: 13369344000 | elapsed time per iteration (s): 0.79 | learning rate: 7.190E-05 | global batch size: 256 | lm loss: 2.127120E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.430 | TFLOPs: 19.57 | +31: iteration 25510/ 39672 | consumed samples: 6530560 | consumed tokens: 13374586880 | elapsed time per iteration (s): 0.81 | learning rate: 7.183E-05 | global batch size: 256 | lm loss: 2.097531E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.599 | TFLOPs: 19.21 | +31: iteration 25520/ 39672 | consumed samples: 6533120 | consumed tokens: 13379829760 | elapsed time per iteration (s): 0.79 | learning rate: 7.177E-05 | global batch size: 256 | lm loss: 2.116365E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.394 | TFLOPs: 19.69 | +31: iteration 25530/ 39672 | consumed samples: 6535680 | consumed tokens: 13385072640 | elapsed time per iteration (s): 0.78 | learning rate: 7.170E-05 | global batch size: 256 | lm loss: 2.122772E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.173 | TFLOPs: 19.97 | +31: iteration 25540/ 39672 | consumed samples: 6538240 | consumed tokens: 13390315520 | elapsed time per iteration (s): 0.83 | learning rate: 7.164E-05 | global batch size: 256 | lm loss: 2.121281E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.640 | TFLOPs: 18.67 | +31: iteration 25550/ 39672 | consumed samples: 6540800 | consumed tokens: 13395558400 | elapsed time per iteration (s): 0.85 | learning rate: 7.157E-05 | global batch size: 256 | lm loss: 2.121733E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.354 | TFLOPs: 18.17 | +31: iteration 25560/ 39672 | consumed samples: 6543360 | consumed tokens: 13400801280 | elapsed time per iteration (s): 0.85 | learning rate: 7.151E-05 | global batch size: 256 | lm loss: 2.134509E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.045 | TFLOPs: 18.27 | +31: iteration 25570/ 39672 | consumed samples: 6545920 | consumed tokens: 13406044160 | elapsed time per iteration (s): 0.84 | learning rate: 7.144E-05 | global batch size: 256 | lm loss: 2.116559E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.188 | TFLOPs: 18.46 | +31: iteration 25580/ 39672 | consumed samples: 6548480 | consumed tokens: 13411287040 | elapsed time per iteration (s): 0.80 | learning rate: 7.138E-05 | global batch size: 256 | lm loss: 2.103558E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.957 | TFLOPs: 19.30 | +31: iteration 25590/ 39672 | consumed samples: 6551040 | consumed tokens: 13416529920 | elapsed time per iteration (s): 0.83 | learning rate: 7.131E-05 | global batch size: 256 | lm loss: 2.109970E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.665 | TFLOPs: 18.67 | +31: iteration 25600/ 39672 | consumed samples: 6553600 | consumed tokens: 13421772800 | elapsed time per iteration (s): 0.81 | learning rate: 7.125E-05 | global batch size: 256 | lm loss: 2.111090E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.862 | TFLOPs: 19.17 | +31: iteration 25610/ 39672 | consumed samples: 6556160 | consumed tokens: 13427015680 | elapsed time per iteration (s): 0.79 | learning rate: 7.118E-05 | global batch size: 256 | lm loss: 2.125295E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.637 | TFLOPs: 19.52 | +31: iteration 25620/ 39672 | consumed samples: 6558720 | consumed tokens: 13432258560 | elapsed time per iteration (s): 0.78 | learning rate: 7.112E-05 | global batch size: 256 | lm loss: 2.151080E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.054 | TFLOPs: 19.79 | +31: iteration 25630/ 39672 | consumed samples: 6561280 | consumed tokens: 13437501440 | elapsed time per iteration (s): 0.80 | learning rate: 7.105E-05 | global batch size: 256 | lm loss: 2.146015E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.702 | TFLOPs: 19.34 | +31: iteration 25640/ 39672 | consumed samples: 6563840 | consumed tokens: 13442744320 | elapsed time per iteration (s): 0.83 | learning rate: 7.099E-05 | global batch size: 256 | lm loss: 2.127005E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.604 | TFLOPs: 18.73 | +31: iteration 25650/ 39672 | consumed samples: 6566400 | consumed tokens: 13447987200 | elapsed time per iteration (s): 0.83 | learning rate: 7.092E-05 | global batch size: 256 | lm loss: 2.142689E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.482 | TFLOPs: 18.60 | +31: iteration 25660/ 39672 | consumed samples: 6568960 | consumed tokens: 13453230080 | elapsed time per iteration (s): 0.80 | learning rate: 7.086E-05 | global batch size: 256 | lm loss: 2.143472E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.538 | TFLOPs: 19.27 | +31: iteration 25670/ 39672 | consumed samples: 6571520 | consumed tokens: 13458472960 | elapsed time per iteration (s): 0.81 | learning rate: 7.079E-05 | global batch size: 256 | lm loss: 2.133598E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.922 | TFLOPs: 19.23 | +31: iteration 25680/ 39672 | consumed samples: 6574080 | consumed tokens: 13463715840 | elapsed time per iteration (s): 0.89 | learning rate: 7.073E-05 | global batch size: 256 | lm loss: 2.118155E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 288.330 | TFLOPs: 17.44 | +31: iteration 25690/ 39672 | consumed samples: 6576640 | consumed tokens: 13468958720 | elapsed time per iteration (s): 0.81 | learning rate: 7.066E-05 | global batch size: 256 | lm loss: 2.127705E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.937 | TFLOPs: 19.17 | +31: iteration 25700/ 39672 | consumed samples: 6579200 | consumed tokens: 13474201600 | elapsed time per iteration (s): 0.88 | learning rate: 7.060E-05 | global batch size: 256 | lm loss: 2.143964E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 291.507 | TFLOPs: 17.64 | +31: iteration 25710/ 39672 | consumed samples: 6581760 | consumed tokens: 13479444480 | elapsed time per iteration (s): 0.84 | learning rate: 7.053E-05 | global batch size: 256 | lm loss: 2.101979E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.573 | TFLOPs: 18.43 | +31: iteration 25720/ 39672 | consumed samples: 6584320 | consumed tokens: 13484687360 | elapsed time per iteration (s): 0.79 | learning rate: 7.047E-05 | global batch size: 256 | lm loss: 2.124682E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.546 | TFLOPs: 19.63 | +31: iteration 25730/ 39672 | consumed samples: 6586880 | consumed tokens: 13489930240 | elapsed time per iteration (s): 0.79 | learning rate: 7.040E-05 | global batch size: 256 | lm loss: 2.122590E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.090 | TFLOPs: 19.73 | +31: iteration 25740/ 39672 | consumed samples: 6589440 | consumed tokens: 13495173120 | elapsed time per iteration (s): 0.82 | learning rate: 7.034E-05 | global batch size: 256 | lm loss: 2.127418E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.259 | TFLOPs: 18.89 | +31: iteration 25750/ 39672 | consumed samples: 6592000 | consumed tokens: 13500416000 | elapsed time per iteration (s): 0.75 | learning rate: 7.028E-05 | global batch size: 256 | lm loss: 2.130014E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.039 | TFLOPs: 20.63 | +31: iteration 25760/ 39672 | consumed samples: 6594560 | consumed tokens: 13505658880 | elapsed time per iteration (s): 0.75 | learning rate: 7.021E-05 | global batch size: 256 | lm loss: 2.153852E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.912 | TFLOPs: 20.75 | +31: iteration 25770/ 39672 | consumed samples: 6597120 | consumed tokens: 13510901760 | elapsed time per iteration (s): 0.76 | learning rate: 7.015E-05 | global batch size: 256 | lm loss: 2.127907E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.621 | TFLOPs: 20.30 | +31: iteration 25780/ 39672 | consumed samples: 6599680 | consumed tokens: 13516144640 | elapsed time per iteration (s): 0.72 | learning rate: 7.008E-05 | global batch size: 256 | lm loss: 2.115608E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.874 | TFLOPs: 21.47 | +31: iteration 25790/ 39672 | consumed samples: 6602240 | consumed tokens: 13521387520 | elapsed time per iteration (s): 0.76 | learning rate: 7.002E-05 | global batch size: 256 | lm loss: 2.147179E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.836 | TFLOPs: 20.50 | +31: iteration 25800/ 39672 | consumed samples: 6604800 | consumed tokens: 13526630400 | elapsed time per iteration (s): 0.75 | learning rate: 6.995E-05 | global batch size: 256 | lm loss: 2.123000E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.487 | TFLOPs: 20.78 | +31: iteration 25810/ 39672 | consumed samples: 6607360 | consumed tokens: 13531873280 | elapsed time per iteration (s): 0.84 | learning rate: 6.989E-05 | global batch size: 256 | lm loss: 2.145576E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.824 | TFLOPs: 18.44 | +31: iteration 25820/ 39672 | consumed samples: 6609920 | consumed tokens: 13537116160 | elapsed time per iteration (s): 0.84 | learning rate: 6.982E-05 | global batch size: 256 | lm loss: 2.142296E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.566 | TFLOPs: 18.49 | +31: iteration 25830/ 39672 | consumed samples: 6612480 | consumed tokens: 13542359040 | elapsed time per iteration (s): 0.85 | learning rate: 6.976E-05 | global batch size: 256 | lm loss: 2.128323E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.917 | TFLOPs: 18.14 | +31: iteration 25840/ 39672 | consumed samples: 6615040 | consumed tokens: 13547601920 | elapsed time per iteration (s): 0.76 | learning rate: 6.969E-05 | global batch size: 256 | lm loss: 2.123513E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.991 | TFLOPs: 20.33 | +31: iteration 25850/ 39672 | consumed samples: 6617600 | consumed tokens: 13552844800 | elapsed time per iteration (s): 0.74 | learning rate: 6.963E-05 | global batch size: 256 | lm loss: 2.143219E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.789 | TFLOPs: 20.86 | +31: iteration 25860/ 39672 | consumed samples: 6620160 | consumed tokens: 13558087680 | elapsed time per iteration (s): 0.75 | learning rate: 6.957E-05 | global batch size: 256 | lm loss: 2.138070E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.704 | TFLOPs: 20.55 | +31: iteration 25870/ 39672 | consumed samples: 6622720 | consumed tokens: 13563330560 | elapsed time per iteration (s): 0.78 | learning rate: 6.950E-05 | global batch size: 256 | lm loss: 2.125108E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.747 | TFLOPs: 19.77 | +31: iteration 25880/ 39672 | consumed samples: 6625280 | consumed tokens: 13568573440 | elapsed time per iteration (s): 0.80 | learning rate: 6.944E-05 | global batch size: 256 | lm loss: 2.102295E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.482 | TFLOPs: 19.27 | +31: iteration 25890/ 39672 | consumed samples: 6627840 | consumed tokens: 13573816320 | elapsed time per iteration (s): 0.76 | learning rate: 6.937E-05 | global batch size: 256 | lm loss: 2.109326E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.691 | TFLOPs: 20.31 | +31: iteration 25900/ 39672 | consumed samples: 6630400 | consumed tokens: 13579059200 | elapsed time per iteration (s): 0.80 | learning rate: 6.931E-05 | global batch size: 256 | lm loss: 2.134290E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.338 | TFLOPs: 19.38 | +31: iteration 25910/ 39672 | consumed samples: 6632960 | consumed tokens: 13584302080 | elapsed time per iteration (s): 0.77 | learning rate: 6.924E-05 | global batch size: 256 | lm loss: 2.131405E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.070 | TFLOPs: 20.15 | +31: iteration 25920/ 39672 | consumed samples: 6635520 | consumed tokens: 13589544960 | elapsed time per iteration (s): 0.77 | learning rate: 6.918E-05 | global batch size: 256 | lm loss: 2.117639E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.071 | TFLOPs: 20.03 | +31: iteration 25930/ 39672 | consumed samples: 6638080 | consumed tokens: 13594787840 | elapsed time per iteration (s): 0.75 | learning rate: 6.912E-05 | global batch size: 256 | lm loss: 2.132626E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.683 | TFLOPs: 20.67 | +31: iteration 25940/ 39672 | consumed samples: 6640640 | consumed tokens: 13600030720 | elapsed time per iteration (s): 1.02 | learning rate: 6.905E-05 | global batch size: 256 | lm loss: 2.114199E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 249.766 | TFLOPs: 15.11 | +31: iteration 25950/ 39672 | consumed samples: 6643200 | consumed tokens: 13605273600 | elapsed time per iteration (s): 0.79 | learning rate: 6.899E-05 | global batch size: 256 | lm loss: 2.133199E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.009 | TFLOPs: 19.72 | +31: iteration 25960/ 39672 | consumed samples: 6645760 | consumed tokens: 13610516480 | elapsed time per iteration (s): 0.77 | learning rate: 6.892E-05 | global batch size: 256 | lm loss: 2.119093E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.201 | TFLOPs: 20.16 | +31: iteration 25970/ 39672 | consumed samples: 6648320 | consumed tokens: 13615759360 | elapsed time per iteration (s): 0.73 | learning rate: 6.886E-05 | global batch size: 256 | lm loss: 2.136244E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.655 | TFLOPs: 21.33 | +31: iteration 25980/ 39672 | consumed samples: 6650880 | consumed tokens: 13621002240 | elapsed time per iteration (s): 0.83 | learning rate: 6.880E-05 | global batch size: 256 | lm loss: 2.107150E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.348 | TFLOPs: 18.71 | +31: iteration 25990/ 39672 | consumed samples: 6653440 | consumed tokens: 13626245120 | elapsed time per iteration (s): 0.75 | learning rate: 6.873E-05 | global batch size: 256 | lm loss: 2.137739E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.457 | TFLOPs: 20.66 | + 0: [2022-11-30 14:58:01,465] [INFO] [logging.py:68:log_dist] [Rank 0] step=26000, skipped=0, lr=[6.866825803145002e-05, 6.866825803145002e-05, 6.866825803145002e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 26000/ 39672 | consumed samples: 6656000 | consumed tokens: 13631488000 | elapsed time per iteration (s): 0.78 | learning rate: 6.867E-05 | global batch size: 256 | lm loss: 2.145418E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.887 | TFLOPs: 19.78 | + 0: steps: 26000 loss: 2.1797 iter time (s): 0.795 samples/sec: 321.945 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 26000 | lm loss value: 2.045492E+00 | lm loss PPL: 7.732960E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 26010/ 39672 | consumed samples: 6658560 | consumed tokens: 13636730880 | elapsed time per iteration (s): 0.77 | learning rate: 6.860E-05 | global batch size: 256 | lm loss: 2.109669E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.970 | TFLOPs: 20.08 | +31: iteration 26020/ 39672 | consumed samples: 6661120 | consumed tokens: 13641973760 | elapsed time per iteration (s): 0.76 | learning rate: 6.854E-05 | global batch size: 256 | lm loss: 2.127521E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.652 | TFLOPs: 20.43 | +31: iteration 26030/ 39672 | consumed samples: 6663680 | consumed tokens: 13647216640 | elapsed time per iteration (s): 0.75 | learning rate: 6.848E-05 | global batch size: 256 | lm loss: 2.151640E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.852 | TFLOPs: 20.74 | +31: iteration 26040/ 39672 | consumed samples: 6666240 | consumed tokens: 13652459520 | elapsed time per iteration (s): 0.72 | learning rate: 6.841E-05 | global batch size: 256 | lm loss: 2.109824E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.291 | TFLOPs: 21.43 | +31: iteration 26050/ 39672 | consumed samples: 6668800 | consumed tokens: 13657702400 | elapsed time per iteration (s): 0.79 | learning rate: 6.835E-05 | global batch size: 256 | lm loss: 2.122906E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.869 | TFLOPs: 19.59 | +31: iteration 26060/ 39672 | consumed samples: 6671360 | consumed tokens: 13662945280 | elapsed time per iteration (s): 0.81 | learning rate: 6.829E-05 | global batch size: 256 | lm loss: 2.154106E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.416 | TFLOPs: 19.02 | +31: iteration 26070/ 39672 | consumed samples: 6673920 | consumed tokens: 13668188160 | elapsed time per iteration (s): 0.82 | learning rate: 6.822E-05 | global batch size: 256 | lm loss: 2.116968E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.858 | TFLOPs: 18.81 | +31: iteration 26080/ 39672 | consumed samples: 6676480 | consumed tokens: 13673431040 | elapsed time per iteration (s): 0.83 | learning rate: 6.816E-05 | global batch size: 256 | lm loss: 2.125641E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.774 | TFLOPs: 18.56 | +31: iteration 26090/ 39672 | consumed samples: 6679040 | consumed tokens: 13678673920 | elapsed time per iteration (s): 0.83 | learning rate: 6.809E-05 | global batch size: 256 | lm loss: 2.105137E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.928 | TFLOPs: 18.75 | +31: iteration 26100/ 39672 | consumed samples: 6681600 | consumed tokens: 13683916800 | elapsed time per iteration (s): 0.82 | learning rate: 6.803E-05 | global batch size: 256 | lm loss: 2.128962E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.811 | TFLOPs: 18.80 | +31: iteration 26110/ 39672 | consumed samples: 6684160 | consumed tokens: 13689159680 | elapsed time per iteration (s): 0.84 | learning rate: 6.797E-05 | global batch size: 256 | lm loss: 2.130266E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.645 | TFLOPs: 18.43 | +31: iteration 26120/ 39672 | consumed samples: 6686720 | consumed tokens: 13694402560 | elapsed time per iteration (s): 0.83 | learning rate: 6.790E-05 | global batch size: 256 | lm loss: 2.117571E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.441 | TFLOPs: 18.66 | +31: iteration 26130/ 39672 | consumed samples: 6689280 | consumed tokens: 13699645440 | elapsed time per iteration (s): 0.82 | learning rate: 6.784E-05 | global batch size: 256 | lm loss: 2.117534E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.958 | TFLOPs: 18.81 | +31: iteration 26140/ 39672 | consumed samples: 6691840 | consumed tokens: 13704888320 | elapsed time per iteration (s): 0.79 | learning rate: 6.778E-05 | global batch size: 256 | lm loss: 2.114972E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.745 | TFLOPs: 19.71 | +31: iteration 26150/ 39672 | consumed samples: 6694400 | consumed tokens: 13710131200 | elapsed time per iteration (s): 0.84 | learning rate: 6.771E-05 | global batch size: 256 | lm loss: 2.107804E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.213 | TFLOPs: 18.53 | +31: iteration 26160/ 39672 | consumed samples: 6696960 | consumed tokens: 13715374080 | elapsed time per iteration (s): 0.78 | learning rate: 6.765E-05 | global batch size: 256 | lm loss: 2.087085E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.982 | TFLOPs: 19.90 | +31: iteration 26170/ 39672 | consumed samples: 6699520 | consumed tokens: 13720616960 | elapsed time per iteration (s): 0.83 | learning rate: 6.758E-05 | global batch size: 256 | lm loss: 2.118783E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.399 | TFLOPs: 18.66 | +31: iteration 26180/ 39672 | consumed samples: 6702080 | consumed tokens: 13725859840 | elapsed time per iteration (s): 0.81 | learning rate: 6.752E-05 | global batch size: 256 | lm loss: 2.116371E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.851 | TFLOPs: 19.05 | +31: iteration 26190/ 39672 | consumed samples: 6704640 | consumed tokens: 13731102720 | elapsed time per iteration (s): 0.80 | learning rate: 6.746E-05 | global batch size: 256 | lm loss: 2.120652E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.935 | TFLOPs: 19.29 | +31: iteration 26200/ 39672 | consumed samples: 6707200 | consumed tokens: 13736345600 | elapsed time per iteration (s): 0.86 | learning rate: 6.739E-05 | global batch size: 256 | lm loss: 2.127932E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.405 | TFLOPs: 18.11 | +31: iteration 26210/ 39672 | consumed samples: 6709760 | consumed tokens: 13741588480 | elapsed time per iteration (s): 0.83 | learning rate: 6.733E-05 | global batch size: 256 | lm loss: 2.127365E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.211 | TFLOPs: 18.59 | +31: iteration 26220/ 39672 | consumed samples: 6712320 | consumed tokens: 13746831360 | elapsed time per iteration (s): 0.84 | learning rate: 6.727E-05 | global batch size: 256 | lm loss: 2.147034E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.354 | TFLOPs: 18.35 | +31: iteration 26230/ 39672 | consumed samples: 6714880 | consumed tokens: 13752074240 | elapsed time per iteration (s): 0.80 | learning rate: 6.720E-05 | global batch size: 256 | lm loss: 2.109749E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.287 | TFLOPs: 19.26 | +31: iteration 26240/ 39672 | consumed samples: 6717440 | consumed tokens: 13757317120 | elapsed time per iteration (s): 0.86 | learning rate: 6.714E-05 | global batch size: 256 | lm loss: 2.107369E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.654 | TFLOPs: 18.07 | +31: iteration 26250/ 39672 | consumed samples: 6720000 | consumed tokens: 13762560000 | elapsed time per iteration (s): 0.81 | learning rate: 6.708E-05 | global batch size: 256 | lm loss: 2.107076E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.951 | TFLOPs: 19.24 | +31: iteration 26260/ 39672 | consumed samples: 6722560 | consumed tokens: 13767802880 | elapsed time per iteration (s): 0.78 | learning rate: 6.701E-05 | global batch size: 256 | lm loss: 2.110642E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.615 | TFLOPs: 19.76 | +31: iteration 26270/ 39672 | consumed samples: 6725120 | consumed tokens: 13773045760 | elapsed time per iteration (s): 0.81 | learning rate: 6.695E-05 | global batch size: 256 | lm loss: 2.112951E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.870 | TFLOPs: 19.23 | +31: iteration 26280/ 39672 | consumed samples: 6727680 | consumed tokens: 13778288640 | elapsed time per iteration (s): 0.78 | learning rate: 6.689E-05 | global batch size: 256 | lm loss: 2.120058E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.223 | TFLOPs: 19.74 | +31: iteration 26290/ 39672 | consumed samples: 6730240 | consumed tokens: 13783531520 | elapsed time per iteration (s): 0.75 | learning rate: 6.683E-05 | global batch size: 256 | lm loss: 2.139257E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.448 | TFLOPs: 20.72 | +31: iteration 26300/ 39672 | consumed samples: 6732800 | consumed tokens: 13788774400 | elapsed time per iteration (s): 0.78 | learning rate: 6.676E-05 | global batch size: 256 | lm loss: 2.124158E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.231 | TFLOPs: 19.92 | +31: iteration 26310/ 39672 | consumed samples: 6735360 | consumed tokens: 13794017280 | elapsed time per iteration (s): 0.78 | learning rate: 6.670E-05 | global batch size: 256 | lm loss: 2.128131E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.553 | TFLOPs: 19.76 | +31: iteration 26320/ 39672 | consumed samples: 6737920 | consumed tokens: 13799260160 | elapsed time per iteration (s): 0.76 | learning rate: 6.664E-05 | global batch size: 256 | lm loss: 2.130541E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.816 | TFLOPs: 20.32 | +31: iteration 26330/ 39672 | consumed samples: 6740480 | consumed tokens: 13804503040 | elapsed time per iteration (s): 0.78 | learning rate: 6.657E-05 | global batch size: 256 | lm loss: 2.154308E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.891 | TFLOPs: 19.84 | +31: iteration 26340/ 39672 | consumed samples: 6743040 | consumed tokens: 13809745920 | elapsed time per iteration (s): 0.82 | learning rate: 6.651E-05 | global batch size: 256 | lm loss: 2.138519E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.969 | TFLOPs: 18.99 | +31: iteration 26350/ 39672 | consumed samples: 6745600 | consumed tokens: 13814988800 | elapsed time per iteration (s): 0.81 | learning rate: 6.645E-05 | global batch size: 256 | lm loss: 2.120483E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.206 | TFLOPs: 19.01 | +31: iteration 26360/ 39672 | consumed samples: 6748160 | consumed tokens: 13820231680 | elapsed time per iteration (s): 0.77 | learning rate: 6.638E-05 | global batch size: 256 | lm loss: 2.088922E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.431 | TFLOPs: 20.05 | +31: iteration 26370/ 39672 | consumed samples: 6750720 | consumed tokens: 13825474560 | elapsed time per iteration (s): 0.78 | learning rate: 6.632E-05 | global batch size: 256 | lm loss: 2.128470E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.179 | TFLOPs: 19.97 | +31: iteration 26380/ 39672 | consumed samples: 6753280 | consumed tokens: 13830717440 | elapsed time per iteration (s): 0.75 | learning rate: 6.626E-05 | global batch size: 256 | lm loss: 2.137473E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.228 | TFLOPs: 20.58 | +31: iteration 26390/ 39672 | consumed samples: 6755840 | consumed tokens: 13835960320 | elapsed time per iteration (s): 0.78 | learning rate: 6.619E-05 | global batch size: 256 | lm loss: 2.147445E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.416 | TFLOPs: 19.75 | +31: iteration 26400/ 39672 | consumed samples: 6758400 | consumed tokens: 13841203200 | elapsed time per iteration (s): 0.74 | learning rate: 6.613E-05 | global batch size: 256 | lm loss: 2.108809E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.801 | TFLOPs: 20.86 | +31: iteration 26410/ 39672 | consumed samples: 6760960 | consumed tokens: 13846446080 | elapsed time per iteration (s): 0.78 | learning rate: 6.607E-05 | global batch size: 256 | lm loss: 2.145491E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.401 | TFLOPs: 19.87 | +31: iteration 26420/ 39672 | consumed samples: 6763520 | consumed tokens: 13851688960 | elapsed time per iteration (s): 0.80 | learning rate: 6.601E-05 | global batch size: 256 | lm loss: 2.109351E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.287 | TFLOPs: 19.26 | +31: iteration 26430/ 39672 | consumed samples: 6766080 | consumed tokens: 13856931840 | elapsed time per iteration (s): 0.81 | learning rate: 6.594E-05 | global batch size: 256 | lm loss: 2.077104E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.292 | TFLOPs: 19.13 | +31: iteration 26440/ 39672 | consumed samples: 6768640 | consumed tokens: 13862174720 | elapsed time per iteration (s): 0.77 | learning rate: 6.588E-05 | global batch size: 256 | lm loss: 2.173765E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.205 | TFLOPs: 20.16 | +31: iteration 26450/ 39672 | consumed samples: 6771200 | consumed tokens: 13867417600 | elapsed time per iteration (s): 0.79 | learning rate: 6.582E-05 | global batch size: 256 | lm loss: 2.111008E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.252 | TFLOPs: 19.68 | +31: iteration 26460/ 39672 | consumed samples: 6773760 | consumed tokens: 13872660480 | elapsed time per iteration (s): 0.87 | learning rate: 6.576E-05 | global batch size: 256 | lm loss: 2.123470E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.409 | TFLOPs: 17.87 | +31: iteration 26470/ 39672 | consumed samples: 6776320 | consumed tokens: 13877903360 | elapsed time per iteration (s): 0.82 | learning rate: 6.569E-05 | global batch size: 256 | lm loss: 2.103201E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.131 | TFLOPs: 18.82 | +31: iteration 26480/ 39672 | consumed samples: 6778880 | consumed tokens: 13883146240 | elapsed time per iteration (s): 0.77 | learning rate: 6.563E-05 | global batch size: 256 | lm loss: 2.112645E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.556 | TFLOPs: 20.00 | +31: iteration 26490/ 39672 | consumed samples: 6781440 | consumed tokens: 13888389120 | elapsed time per iteration (s): 0.77 | learning rate: 6.557E-05 | global batch size: 256 | lm loss: 2.104995E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.414 | TFLOPs: 20.17 | +31: iteration 26500/ 39672 | consumed samples: 6784000 | consumed tokens: 13893632000 | elapsed time per iteration (s): 0.76 | learning rate: 6.550E-05 | global batch size: 256 | lm loss: 2.121511E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.645 | TFLOPs: 20.43 | +31: iteration 26510/ 39672 | consumed samples: 6786560 | consumed tokens: 13898874880 | elapsed time per iteration (s): 0.78 | learning rate: 6.544E-05 | global batch size: 256 | lm loss: 2.128175E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.002 | TFLOPs: 19.78 | +31: iteration 26520/ 39672 | consumed samples: 6789120 | consumed tokens: 13904117760 | elapsed time per iteration (s): 0.76 | learning rate: 6.538E-05 | global batch size: 256 | lm loss: 2.124111E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.918 | TFLOPs: 20.26 | +31: iteration 26530/ 39672 | consumed samples: 6791680 | consumed tokens: 13909360640 | elapsed time per iteration (s): 0.81 | learning rate: 6.532E-05 | global batch size: 256 | lm loss: 2.122659E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.532 | TFLOPs: 19.15 | +31: iteration 26540/ 39672 | consumed samples: 6794240 | consumed tokens: 13914603520 | elapsed time per iteration (s): 0.77 | learning rate: 6.525E-05 | global batch size: 256 | lm loss: 2.106355E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.584 | TFLOPs: 20.24 | +31: iteration 26550/ 39672 | consumed samples: 6796800 | consumed tokens: 13919846400 | elapsed time per iteration (s): 0.83 | learning rate: 6.519E-05 | global batch size: 256 | lm loss: 2.136559E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.853 | TFLOPs: 18.56 | +31: iteration 26560/ 39672 | consumed samples: 6799360 | consumed tokens: 13925089280 | elapsed time per iteration (s): 0.81 | learning rate: 6.513E-05 | global batch size: 256 | lm loss: 2.117741E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.376 | TFLOPs: 19.14 | +31: iteration 26570/ 39672 | consumed samples: 6801920 | consumed tokens: 13930332160 | elapsed time per iteration (s): 0.77 | learning rate: 6.507E-05 | global batch size: 256 | lm loss: 2.085299E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.663 | TFLOPs: 20.00 | +31: iteration 26580/ 39672 | consumed samples: 6804480 | consumed tokens: 13935575040 | elapsed time per iteration (s): 0.76 | learning rate: 6.501E-05 | global batch size: 256 | lm loss: 2.126761E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.357 | TFLOPs: 20.47 | +31: iteration 26590/ 39672 | consumed samples: 6807040 | consumed tokens: 13940817920 | elapsed time per iteration (s): 0.75 | learning rate: 6.494E-05 | global batch size: 256 | lm loss: 2.103547E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.478 | TFLOPs: 20.72 | +31: iteration 26600/ 39672 | consumed samples: 6809600 | consumed tokens: 13946060800 | elapsed time per iteration (s): 0.76 | learning rate: 6.488E-05 | global batch size: 256 | lm loss: 2.118113E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.063 | TFLOPs: 20.45 | +31: iteration 26610/ 39672 | consumed samples: 6812160 | consumed tokens: 13951303680 | elapsed time per iteration (s): 0.77 | learning rate: 6.482E-05 | global batch size: 256 | lm loss: 2.116620E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.334 | TFLOPs: 20.11 | +31: iteration 26620/ 39672 | consumed samples: 6814720 | consumed tokens: 13956546560 | elapsed time per iteration (s): 0.79 | learning rate: 6.476E-05 | global batch size: 256 | lm loss: 2.120942E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.613 | TFLOPs: 19.70 | +31: iteration 26630/ 39672 | consumed samples: 6817280 | consumed tokens: 13961789440 | elapsed time per iteration (s): 0.75 | learning rate: 6.469E-05 | global batch size: 256 | lm loss: 2.116957E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.507 | TFLOPs: 20.66 | +31: iteration 26640/ 39672 | consumed samples: 6819840 | consumed tokens: 13967032320 | elapsed time per iteration (s): 0.75 | learning rate: 6.463E-05 | global batch size: 256 | lm loss: 2.130037E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.207 | TFLOPs: 20.64 | +31: iteration 26650/ 39672 | consumed samples: 6822400 | consumed tokens: 13972275200 | elapsed time per iteration (s): 0.80 | learning rate: 6.457E-05 | global batch size: 256 | lm loss: 2.104634E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.747 | TFLOPs: 19.40 | +31: iteration 26660/ 39672 | consumed samples: 6824960 | consumed tokens: 13977518080 | elapsed time per iteration (s): 0.80 | learning rate: 6.451E-05 | global batch size: 256 | lm loss: 2.100883E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.459 | TFLOPs: 19.27 | +31: iteration 26670/ 39672 | consumed samples: 6827520 | consumed tokens: 13982760960 | elapsed time per iteration (s): 0.82 | learning rate: 6.445E-05 | global batch size: 256 | lm loss: 2.136805E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.408 | TFLOPs: 18.96 | +31: iteration 26680/ 39672 | consumed samples: 6830080 | consumed tokens: 13988003840 | elapsed time per iteration (s): 0.76 | learning rate: 6.438E-05 | global batch size: 256 | lm loss: 2.147882E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.197 | TFLOPs: 20.46 | +31: iteration 26690/ 39672 | consumed samples: 6832640 | consumed tokens: 13993246720 | elapsed time per iteration (s): 0.74 | learning rate: 6.432E-05 | global batch size: 256 | lm loss: 2.092332E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.246 | TFLOPs: 20.83 | +31: iteration 26700/ 39672 | consumed samples: 6835200 | consumed tokens: 13998489600 | elapsed time per iteration (s): 0.76 | learning rate: 6.426E-05 | global batch size: 256 | lm loss: 2.132830E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.335 | TFLOPs: 20.35 | +31: iteration 26710/ 39672 | consumed samples: 6837760 | consumed tokens: 14003732480 | elapsed time per iteration (s): 0.73 | learning rate: 6.420E-05 | global batch size: 256 | lm loss: 2.105062E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.454 | TFLOPs: 21.08 | +31: iteration 26720/ 39672 | consumed samples: 6840320 | consumed tokens: 14008975360 | elapsed time per iteration (s): 0.76 | learning rate: 6.414E-05 | global batch size: 256 | lm loss: 2.124286E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.942 | TFLOPs: 20.44 | +31: iteration 26730/ 39672 | consumed samples: 6842880 | consumed tokens: 14014218240 | elapsed time per iteration (s): 0.76 | learning rate: 6.407E-05 | global batch size: 256 | lm loss: 2.116438E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.671 | TFLOPs: 20.37 | +31: iteration 26740/ 39672 | consumed samples: 6845440 | consumed tokens: 14019461120 | elapsed time per iteration (s): 0.75 | learning rate: 6.401E-05 | global batch size: 256 | lm loss: 2.106388E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.216 | TFLOPs: 20.58 | +31: iteration 26750/ 39672 | consumed samples: 6848000 | consumed tokens: 14024704000 | elapsed time per iteration (s): 0.78 | learning rate: 6.395E-05 | global batch size: 256 | lm loss: 2.126848E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.539 | TFLOPs: 19.82 | +31: iteration 26760/ 39672 | consumed samples: 6850560 | consumed tokens: 14029946880 | elapsed time per iteration (s): 0.74 | learning rate: 6.389E-05 | global batch size: 256 | lm loss: 2.111164E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.299 | TFLOPs: 20.83 | +31: iteration 26770/ 39672 | consumed samples: 6853120 | consumed tokens: 14035189760 | elapsed time per iteration (s): 0.80 | learning rate: 6.383E-05 | global batch size: 256 | lm loss: 2.135648E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.265 | TFLOPs: 19.44 | +31: iteration 26780/ 39672 | consumed samples: 6855680 | consumed tokens: 14040432640 | elapsed time per iteration (s): 0.79 | learning rate: 6.376E-05 | global batch size: 256 | lm loss: 2.128404E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.642 | TFLOPs: 19.58 | +31: iteration 26790/ 39672 | consumed samples: 6858240 | consumed tokens: 14045675520 | elapsed time per iteration (s): 0.77 | learning rate: 6.370E-05 | global batch size: 256 | lm loss: 2.097683E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.420 | TFLOPs: 20.23 | +31: iteration 26800/ 39672 | consumed samples: 6860800 | consumed tokens: 14050918400 | elapsed time per iteration (s): 0.75 | learning rate: 6.364E-05 | global batch size: 256 | lm loss: 2.117929E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.098 | TFLOPs: 20.51 | +31: iteration 26810/ 39672 | consumed samples: 6863360 | consumed tokens: 14056161280 | elapsed time per iteration (s): 0.78 | learning rate: 6.358E-05 | global batch size: 256 | lm loss: 2.091630E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.405 | TFLOPs: 19.75 | +31: iteration 26820/ 39672 | consumed samples: 6865920 | consumed tokens: 14061404160 | elapsed time per iteration (s): 0.78 | learning rate: 6.352E-05 | global batch size: 256 | lm loss: 2.112989E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.342 | TFLOPs: 19.86 | +31: iteration 26830/ 39672 | consumed samples: 6868480 | consumed tokens: 14066647040 | elapsed time per iteration (s): 0.78 | learning rate: 6.346E-05 | global batch size: 256 | lm loss: 2.082946E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.138 | TFLOPs: 19.97 | +31: iteration 26840/ 39672 | consumed samples: 6871040 | consumed tokens: 14071889920 | elapsed time per iteration (s): 0.78 | learning rate: 6.339E-05 | global batch size: 256 | lm loss: 2.105964E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.650 | TFLOPs: 19.76 | +31: iteration 26850/ 39672 | consumed samples: 6873600 | consumed tokens: 14077132800 | elapsed time per iteration (s): 0.73 | learning rate: 6.333E-05 | global batch size: 256 | lm loss: 2.121849E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.907 | TFLOPs: 21.17 | +31: iteration 26860/ 39672 | consumed samples: 6876160 | consumed tokens: 14082375680 | elapsed time per iteration (s): 0.82 | learning rate: 6.327E-05 | global batch size: 256 | lm loss: 2.107587E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.618 | TFLOPs: 18.85 | +31: iteration 26870/ 39672 | consumed samples: 6878720 | consumed tokens: 14087618560 | elapsed time per iteration (s): 0.74 | learning rate: 6.321E-05 | global batch size: 256 | lm loss: 2.112001E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.630 | TFLOPs: 20.97 | +31: iteration 26880/ 39672 | consumed samples: 6881280 | consumed tokens: 14092861440 | elapsed time per iteration (s): 0.72 | learning rate: 6.315E-05 | global batch size: 256 | lm loss: 2.116260E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.343 | TFLOPs: 21.38 | +31: iteration 26890/ 39672 | consumed samples: 6883840 | consumed tokens: 14098104320 | elapsed time per iteration (s): 0.72 | learning rate: 6.309E-05 | global batch size: 256 | lm loss: 2.105648E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.255 | TFLOPs: 21.37 | +31: iteration 26900/ 39672 | consumed samples: 6886400 | consumed tokens: 14103347200 | elapsed time per iteration (s): 0.76 | learning rate: 6.302E-05 | global batch size: 256 | lm loss: 2.130033E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.323 | TFLOPs: 20.47 | +31: iteration 26910/ 39672 | consumed samples: 6888960 | consumed tokens: 14108590080 | elapsed time per iteration (s): 0.75 | learning rate: 6.296E-05 | global batch size: 256 | lm loss: 2.088582E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.165 | TFLOPs: 20.70 | +31: iteration 26920/ 39672 | consumed samples: 6891520 | consumed tokens: 14113832960 | elapsed time per iteration (s): 0.73 | learning rate: 6.290E-05 | global batch size: 256 | lm loss: 2.125621E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.089 | TFLOPs: 21.30 | +31: iteration 26930/ 39672 | consumed samples: 6894080 | consumed tokens: 14119075840 | elapsed time per iteration (s): 0.73 | learning rate: 6.284E-05 | global batch size: 256 | lm loss: 2.117908E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.099 | TFLOPs: 21.18 | +31: iteration 26940/ 39672 | consumed samples: 6896640 | consumed tokens: 14124318720 | elapsed time per iteration (s): 0.72 | learning rate: 6.278E-05 | global batch size: 256 | lm loss: 2.108217E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.322 | TFLOPs: 21.62 | +31: iteration 26950/ 39672 | consumed samples: 6899200 | consumed tokens: 14129561600 | elapsed time per iteration (s): 0.79 | learning rate: 6.272E-05 | global batch size: 256 | lm loss: 2.116254E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.857 | TFLOPs: 19.59 | +31: iteration 26960/ 39672 | consumed samples: 6901760 | consumed tokens: 14134804480 | elapsed time per iteration (s): 0.72 | learning rate: 6.266E-05 | global batch size: 256 | lm loss: 2.107277E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.312 | TFLOPs: 21.62 | +31: iteration 26970/ 39672 | consumed samples: 6904320 | consumed tokens: 14140047360 | elapsed time per iteration (s): 0.76 | learning rate: 6.260E-05 | global batch size: 256 | lm loss: 2.099005E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.911 | TFLOPs: 20.44 | +31: iteration 26980/ 39672 | consumed samples: 6906880 | consumed tokens: 14145290240 | elapsed time per iteration (s): 0.78 | learning rate: 6.253E-05 | global batch size: 256 | lm loss: 2.118234E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.098 | TFLOPs: 19.91 | +31: iteration 26990/ 39672 | consumed samples: 6909440 | consumed tokens: 14150533120 | elapsed time per iteration (s): 0.79 | learning rate: 6.247E-05 | global batch size: 256 | lm loss: 2.131827E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.887 | TFLOPs: 19.53 | +31: iteration 27000/ 39672 | consumed samples: 6912000 | consumed tokens: 14155776000 | elapsed time per iteration (s): 0.74 | learning rate: 6.241E-05 | global batch size: 256 | lm loss: 2.122151E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.096 | TFLOPs: 21.00 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 27000 | lm loss value: 2.087370E+00 | lm loss PPL: 8.063677E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 27010/ 39672 | consumed samples: 6914560 | consumed tokens: 14161018880 | elapsed time per iteration (s): 0.82 | learning rate: 6.235E-05 | global batch size: 256 | lm loss: 2.122660E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.082 | TFLOPs: 18.82 | +31: iteration 27020/ 39672 | consumed samples: 6917120 | consumed tokens: 14166261760 | elapsed time per iteration (s): 0.73 | learning rate: 6.229E-05 | global batch size: 256 | lm loss: 2.091914E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.576 | TFLOPs: 21.09 | +31: iteration 27030/ 39672 | consumed samples: 6919680 | consumed tokens: 14171504640 | elapsed time per iteration (s): 0.83 | learning rate: 6.223E-05 | global batch size: 256 | lm loss: 2.097850E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.793 | TFLOPs: 18.62 | +31: iteration 27040/ 39672 | consumed samples: 6922240 | consumed tokens: 14176747520 | elapsed time per iteration (s): 0.84 | learning rate: 6.217E-05 | global batch size: 256 | lm loss: 2.101504E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.985 | TFLOPs: 18.51 | +31: iteration 27050/ 39672 | consumed samples: 6924800 | consumed tokens: 14181990400 | elapsed time per iteration (s): 0.80 | learning rate: 6.211E-05 | global batch size: 256 | lm loss: 2.145038E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.857 | TFLOPs: 19.47 | +31: iteration 27060/ 39672 | consumed samples: 6927360 | consumed tokens: 14187233280 | elapsed time per iteration (s): 0.83 | learning rate: 6.205E-05 | global batch size: 256 | lm loss: 2.131900E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.329 | TFLOPs: 18.71 | +31: iteration 27070/ 39672 | consumed samples: 6929920 | consumed tokens: 14192476160 | elapsed time per iteration (s): 0.84 | learning rate: 6.199E-05 | global batch size: 256 | lm loss: 2.112288E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.294 | TFLOPs: 18.41 | +31: iteration 27080/ 39672 | consumed samples: 6932480 | consumed tokens: 14197719040 | elapsed time per iteration (s): 0.81 | learning rate: 6.192E-05 | global batch size: 256 | lm loss: 2.103298E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.179 | TFLOPs: 19.07 | +31: iteration 27090/ 39672 | consumed samples: 6935040 | consumed tokens: 14202961920 | elapsed time per iteration (s): 0.83 | learning rate: 6.186E-05 | global batch size: 256 | lm loss: 2.114397E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.589 | TFLOPs: 18.73 | +31: iteration 27100/ 39672 | consumed samples: 6937600 | consumed tokens: 14208204800 | elapsed time per iteration (s): 0.82 | learning rate: 6.180E-05 | global batch size: 256 | lm loss: 2.099319E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.068 | TFLOPs: 19.00 | +31: iteration 27110/ 39672 | consumed samples: 6940160 | consumed tokens: 14213447680 | elapsed time per iteration (s): 0.82 | learning rate: 6.174E-05 | global batch size: 256 | lm loss: 2.130893E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.191 | TFLOPs: 18.83 | +31: iteration 27120/ 39672 | consumed samples: 6942720 | consumed tokens: 14218690560 | elapsed time per iteration (s): 0.76 | learning rate: 6.168E-05 | global batch size: 256 | lm loss: 2.104760E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.858 | TFLOPs: 20.50 | +31: iteration 27130/ 39672 | consumed samples: 6945280 | consumed tokens: 14223933440 | elapsed time per iteration (s): 0.77 | learning rate: 6.162E-05 | global batch size: 256 | lm loss: 2.122738E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.018 | TFLOPs: 20.09 | +31: iteration 27140/ 39672 | consumed samples: 6947840 | consumed tokens: 14229176320 | elapsed time per iteration (s): 0.77 | learning rate: 6.156E-05 | global batch size: 256 | lm loss: 2.080214E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.572 | TFLOPs: 20.12 | +31: iteration 27150/ 39672 | consumed samples: 6950400 | consumed tokens: 14234419200 | elapsed time per iteration (s): 0.76 | learning rate: 6.150E-05 | global batch size: 256 | lm loss: 2.112015E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.526 | TFLOPs: 20.48 | +31: iteration 27160/ 39672 | consumed samples: 6952960 | consumed tokens: 14239662080 | elapsed time per iteration (s): 0.73 | learning rate: 6.144E-05 | global batch size: 256 | lm loss: 2.137064E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.045 | TFLOPs: 21.12 | +31: iteration 27170/ 39672 | consumed samples: 6955520 | consumed tokens: 14244904960 | elapsed time per iteration (s): 0.80 | learning rate: 6.138E-05 | global batch size: 256 | lm loss: 2.108131E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.751 | TFLOPs: 19.40 | +31: iteration 27180/ 39672 | consumed samples: 6958080 | consumed tokens: 14250147840 | elapsed time per iteration (s): 0.77 | learning rate: 6.132E-05 | global batch size: 256 | lm loss: 2.109523E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.815 | TFLOPs: 20.07 | +31: iteration 27190/ 39672 | consumed samples: 6960640 | consumed tokens: 14255390720 | elapsed time per iteration (s): 0.76 | learning rate: 6.126E-05 | global batch size: 256 | lm loss: 2.116075E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.751 | TFLOPs: 20.25 | +31: iteration 27200/ 39672 | consumed samples: 6963200 | consumed tokens: 14260633600 | elapsed time per iteration (s): 0.79 | learning rate: 6.120E-05 | global batch size: 256 | lm loss: 2.118845E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.913 | TFLOPs: 19.60 | +31: iteration 27210/ 39672 | consumed samples: 6965760 | consumed tokens: 14265876480 | elapsed time per iteration (s): 0.77 | learning rate: 6.114E-05 | global batch size: 256 | lm loss: 2.119067E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.856 | TFLOPs: 20.08 | +31: iteration 27220/ 39672 | consumed samples: 6968320 | consumed tokens: 14271119360 | elapsed time per iteration (s): 0.71 | learning rate: 6.108E-05 | global batch size: 256 | lm loss: 2.114470E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.566 | TFLOPs: 21.75 | +31: iteration 27230/ 39672 | consumed samples: 6970880 | consumed tokens: 14276362240 | elapsed time per iteration (s): 0.75 | learning rate: 6.102E-05 | global batch size: 256 | lm loss: 2.116790E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.109 | TFLOPs: 20.64 | +31: iteration 27240/ 39672 | consumed samples: 6973440 | consumed tokens: 14281605120 | elapsed time per iteration (s): 0.74 | learning rate: 6.095E-05 | global batch size: 256 | lm loss: 2.093409E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.322 | TFLOPs: 20.83 | +31: iteration 27250/ 39672 | consumed samples: 6976000 | consumed tokens: 14286848000 | elapsed time per iteration (s): 0.74 | learning rate: 6.089E-05 | global batch size: 256 | lm loss: 2.109543E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.192 | TFLOPs: 20.82 | +31: iteration 27260/ 39672 | consumed samples: 6978560 | consumed tokens: 14292090880 | elapsed time per iteration (s): 0.73 | learning rate: 6.083E-05 | global batch size: 256 | lm loss: 2.099097E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.466 | TFLOPs: 21.20 | +31: iteration 27270/ 39672 | consumed samples: 6981120 | consumed tokens: 14297333760 | elapsed time per iteration (s): 0.76 | learning rate: 6.077E-05 | global batch size: 256 | lm loss: 2.095932E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.027 | TFLOPs: 20.51 | +31: iteration 27280/ 39672 | consumed samples: 6983680 | consumed tokens: 14302576640 | elapsed time per iteration (s): 0.76 | learning rate: 6.071E-05 | global batch size: 256 | lm loss: 2.114786E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.985 | TFLOPs: 20.27 | +31: iteration 27290/ 39672 | consumed samples: 6986240 | consumed tokens: 14307819520 | elapsed time per iteration (s): 0.76 | learning rate: 6.065E-05 | global batch size: 256 | lm loss: 2.116129E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.419 | TFLOPs: 20.35 | +31: iteration 27300/ 39672 | consumed samples: 6988800 | consumed tokens: 14313062400 | elapsed time per iteration (s): 0.84 | learning rate: 6.059E-05 | global batch size: 256 | lm loss: 2.122171E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.810 | TFLOPs: 18.50 | +31: iteration 27310/ 39672 | consumed samples: 6991360 | consumed tokens: 14318305280 | elapsed time per iteration (s): 0.79 | learning rate: 6.053E-05 | global batch size: 256 | lm loss: 2.121847E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.060 | TFLOPs: 19.48 | +31: iteration 27320/ 39672 | consumed samples: 6993920 | consumed tokens: 14323548160 | elapsed time per iteration (s): 0.78 | learning rate: 6.047E-05 | global batch size: 256 | lm loss: 2.121441E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.299 | TFLOPs: 19.98 | +31: iteration 27330/ 39672 | consumed samples: 6996480 | consumed tokens: 14328791040 | elapsed time per iteration (s): 0.76 | learning rate: 6.041E-05 | global batch size: 256 | lm loss: 2.112693E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.984 | TFLOPs: 20.45 | +31: iteration 27340/ 39672 | consumed samples: 6999040 | consumed tokens: 14334033920 | elapsed time per iteration (s): 0.74 | learning rate: 6.035E-05 | global batch size: 256 | lm loss: 2.109008E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.099 | TFLOPs: 20.82 | +31: iteration 27350/ 39672 | consumed samples: 7001600 | consumed tokens: 14339276800 | elapsed time per iteration (s): 0.73 | learning rate: 6.029E-05 | global batch size: 256 | lm loss: 2.105206E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.835 | TFLOPs: 21.29 | +31: iteration 27360/ 39672 | consumed samples: 7004160 | consumed tokens: 14344519680 | elapsed time per iteration (s): 0.74 | learning rate: 6.023E-05 | global batch size: 256 | lm loss: 2.114302E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.280 | TFLOPs: 21.07 | +31: iteration 27370/ 39672 | consumed samples: 7006720 | consumed tokens: 14349762560 | elapsed time per iteration (s): 0.75 | learning rate: 6.017E-05 | global batch size: 256 | lm loss: 2.152874E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.733 | TFLOPs: 20.61 | +31: iteration 27380/ 39672 | consumed samples: 7009280 | consumed tokens: 14355005440 | elapsed time per iteration (s): 0.79 | learning rate: 6.011E-05 | global batch size: 256 | lm loss: 2.092221E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.020 | TFLOPs: 19.66 | +31: iteration 27390/ 39672 | consumed samples: 7011840 | consumed tokens: 14360248320 | elapsed time per iteration (s): 0.76 | learning rate: 6.005E-05 | global batch size: 256 | lm loss: 2.116963E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.265 | TFLOPs: 20.40 | +31: iteration 27400/ 39672 | consumed samples: 7014400 | consumed tokens: 14365491200 | elapsed time per iteration (s): 0.77 | learning rate: 5.999E-05 | global batch size: 256 | lm loss: 2.097793E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.406 | TFLOPs: 20.11 | +31: iteration 27410/ 39672 | consumed samples: 7016960 | consumed tokens: 14370734080 | elapsed time per iteration (s): 0.75 | learning rate: 5.993E-05 | global batch size: 256 | lm loss: 2.106465E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.389 | TFLOPs: 20.77 | +31: iteration 27420/ 39672 | consumed samples: 7019520 | consumed tokens: 14375976960 | elapsed time per iteration (s): 0.76 | learning rate: 5.987E-05 | global batch size: 256 | lm loss: 2.124835E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.033 | TFLOPs: 20.33 | +31: iteration 27430/ 39672 | consumed samples: 7022080 | consumed tokens: 14381219840 | elapsed time per iteration (s): 0.78 | learning rate: 5.981E-05 | global batch size: 256 | lm loss: 2.121443E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.150 | TFLOPs: 19.97 | +31: iteration 27440/ 39672 | consumed samples: 7024640 | consumed tokens: 14386462720 | elapsed time per iteration (s): 0.72 | learning rate: 5.975E-05 | global batch size: 256 | lm loss: 2.119832E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.754 | TFLOPs: 21.52 | +31: iteration 27450/ 39672 | consumed samples: 7027200 | consumed tokens: 14391705600 | elapsed time per iteration (s): 0.75 | learning rate: 5.969E-05 | global batch size: 256 | lm loss: 2.108273E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.897 | TFLOPs: 20.56 | +31: iteration 27460/ 39672 | consumed samples: 7029760 | consumed tokens: 14396948480 | elapsed time per iteration (s): 0.82 | learning rate: 5.963E-05 | global batch size: 256 | lm loss: 2.131892E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.949 | TFLOPs: 18.93 | +31: iteration 27470/ 39672 | consumed samples: 7032320 | consumed tokens: 14402191360 | elapsed time per iteration (s): 0.76 | learning rate: 5.957E-05 | global batch size: 256 | lm loss: 2.106842E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.552 | TFLOPs: 20.30 | +31: iteration 27480/ 39672 | consumed samples: 7034880 | consumed tokens: 14407434240 | elapsed time per iteration (s): 0.79 | learning rate: 5.952E-05 | global batch size: 256 | lm loss: 2.113032E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.542 | TFLOPs: 19.51 | +31: iteration 27490/ 39672 | consumed samples: 7037440 | consumed tokens: 14412677120 | elapsed time per iteration (s): 0.73 | learning rate: 5.946E-05 | global batch size: 256 | lm loss: 2.125848E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.868 | TFLOPs: 21.35 | +31: iteration 27500/ 39672 | consumed samples: 7040000 | consumed tokens: 14417920000 | elapsed time per iteration (s): 0.78 | learning rate: 5.940E-05 | global batch size: 256 | lm loss: 2.126620E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.070 | TFLOPs: 19.91 | +31: iteration 27510/ 39672 | consumed samples: 7042560 | consumed tokens: 14423162880 | elapsed time per iteration (s): 0.75 | learning rate: 5.934E-05 | global batch size: 256 | lm loss: 2.132286E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.933 | TFLOPs: 20.57 | +31: iteration 27520/ 39672 | consumed samples: 7045120 | consumed tokens: 14428405760 | elapsed time per iteration (s): 0.78 | learning rate: 5.928E-05 | global batch size: 256 | lm loss: 2.096951E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.987 | TFLOPs: 19.90 | +31: iteration 27530/ 39672 | consumed samples: 7047680 | consumed tokens: 14433648640 | elapsed time per iteration (s): 0.74 | learning rate: 5.922E-05 | global batch size: 256 | lm loss: 2.121020E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.034 | TFLOPs: 20.81 | +31: iteration 27540/ 39672 | consumed samples: 7050240 | consumed tokens: 14438891520 | elapsed time per iteration (s): 0.77 | learning rate: 5.916E-05 | global batch size: 256 | lm loss: 2.097654E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.586 | TFLOPs: 20.00 | +31: iteration 27550/ 39672 | consumed samples: 7052800 | consumed tokens: 14444134400 | elapsed time per iteration (s): 0.77 | learning rate: 5.910E-05 | global batch size: 256 | lm loss: 2.104128E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.051 | TFLOPs: 20.21 | +31: iteration 27560/ 39672 | consumed samples: 7055360 | consumed tokens: 14449377280 | elapsed time per iteration (s): 0.80 | learning rate: 5.904E-05 | global batch size: 256 | lm loss: 2.120630E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.568 | TFLOPs: 19.39 | +31: iteration 27570/ 39672 | consumed samples: 7057920 | consumed tokens: 14454620160 | elapsed time per iteration (s): 0.77 | learning rate: 5.898E-05 | global batch size: 256 | lm loss: 2.104560E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.441 | TFLOPs: 19.99 | +31: iteration 27580/ 39672 | consumed samples: 7060480 | consumed tokens: 14459863040 | elapsed time per iteration (s): 0.85 | learning rate: 5.892E-05 | global batch size: 256 | lm loss: 2.113503E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.804 | TFLOPs: 18.14 | +31: iteration 27590/ 39672 | consumed samples: 7063040 | consumed tokens: 14465105920 | elapsed time per iteration (s): 0.83 | learning rate: 5.886E-05 | global batch size: 256 | lm loss: 2.120267E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.916 | TFLOPs: 18.69 | +31: iteration 27600/ 39672 | consumed samples: 7065600 | consumed tokens: 14470348800 | elapsed time per iteration (s): 0.83 | learning rate: 5.880E-05 | global batch size: 256 | lm loss: 2.129069E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.620 | TFLOPs: 18.67 | +31: iteration 27610/ 39672 | consumed samples: 7068160 | consumed tokens: 14475591680 | elapsed time per iteration (s): 0.83 | learning rate: 5.874E-05 | global batch size: 256 | lm loss: 2.109372E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.299 | TFLOPs: 18.71 | +31: iteration 27620/ 39672 | consumed samples: 7070720 | consumed tokens: 14480834560 | elapsed time per iteration (s): 0.85 | learning rate: 5.868E-05 | global batch size: 256 | lm loss: 2.110714E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.531 | TFLOPs: 18.12 | +31: iteration 27630/ 39672 | consumed samples: 7073280 | consumed tokens: 14486077440 | elapsed time per iteration (s): 0.83 | learning rate: 5.862E-05 | global batch size: 256 | lm loss: 2.122604E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.905 | TFLOPs: 18.63 | +31: iteration 27640/ 39672 | consumed samples: 7075840 | consumed tokens: 14491320320 | elapsed time per iteration (s): 0.77 | learning rate: 5.857E-05 | global batch size: 256 | lm loss: 2.121121E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.445 | TFLOPs: 19.99 | +31: iteration 27650/ 39672 | consumed samples: 7078400 | consumed tokens: 14496563200 | elapsed time per iteration (s): 0.71 | learning rate: 5.851E-05 | global batch size: 256 | lm loss: 2.115122E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 358.743 | TFLOPs: 21.70 | +31: iteration 27660/ 39672 | consumed samples: 7080960 | consumed tokens: 14501806080 | elapsed time per iteration (s): 0.82 | learning rate: 5.845E-05 | global batch size: 256 | lm loss: 2.111666E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.975 | TFLOPs: 18.87 | +31: iteration 27670/ 39672 | consumed samples: 7083520 | consumed tokens: 14507048960 | elapsed time per iteration (s): 0.76 | learning rate: 5.839E-05 | global batch size: 256 | lm loss: 2.133044E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.289 | TFLOPs: 20.28 | +31: iteration 27680/ 39672 | consumed samples: 7086080 | consumed tokens: 14512291840 | elapsed time per iteration (s): 0.72 | learning rate: 5.833E-05 | global batch size: 256 | lm loss: 2.126946E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.188 | TFLOPs: 21.55 | +31: iteration 27690/ 39672 | consumed samples: 7088640 | consumed tokens: 14517534720 | elapsed time per iteration (s): 0.75 | learning rate: 5.827E-05 | global batch size: 256 | lm loss: 2.135814E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.137 | TFLOPs: 20.64 | +31: iteration 27700/ 39672 | consumed samples: 7091200 | consumed tokens: 14522777600 | elapsed time per iteration (s): 0.74 | learning rate: 5.821E-05 | global batch size: 256 | lm loss: 2.103475E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.079 | TFLOPs: 20.88 | +31: iteration 27710/ 39672 | consumed samples: 7093760 | consumed tokens: 14528020480 | elapsed time per iteration (s): 0.72 | learning rate: 5.815E-05 | global batch size: 256 | lm loss: 2.144432E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.807 | TFLOPs: 21.40 | +31: iteration 27720/ 39672 | consumed samples: 7096320 | consumed tokens: 14533263360 | elapsed time per iteration (s): 0.72 | learning rate: 5.809E-05 | global batch size: 256 | lm loss: 2.130834E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.867 | TFLOPs: 21.65 | +31: iteration 27730/ 39672 | consumed samples: 7098880 | consumed tokens: 14538506240 | elapsed time per iteration (s): 0.75 | learning rate: 5.804E-05 | global batch size: 256 | lm loss: 2.113538E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.383 | TFLOPs: 20.71 | +31: iteration 27740/ 39672 | consumed samples: 7101440 | consumed tokens: 14543749120 | elapsed time per iteration (s): 0.72 | learning rate: 5.798E-05 | global batch size: 256 | lm loss: 2.118772E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.289 | TFLOPs: 21.55 | +31: iteration 27750/ 39672 | consumed samples: 7104000 | consumed tokens: 14548992000 | elapsed time per iteration (s): 0.76 | learning rate: 5.792E-05 | global batch size: 256 | lm loss: 2.132314E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.928 | TFLOPs: 20.38 | +31: iteration 27760/ 39672 | consumed samples: 7106560 | consumed tokens: 14554234880 | elapsed time per iteration (s): 0.77 | learning rate: 5.786E-05 | global batch size: 256 | lm loss: 2.119080E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.899 | TFLOPs: 20.08 | +31: iteration 27770/ 39672 | consumed samples: 7109120 | consumed tokens: 14559477760 | elapsed time per iteration (s): 0.76 | learning rate: 5.780E-05 | global batch size: 256 | lm loss: 2.093326E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.046 | TFLOPs: 20.45 | +31: iteration 27780/ 39672 | consumed samples: 7111680 | consumed tokens: 14564720640 | elapsed time per iteration (s): 0.77 | learning rate: 5.774E-05 | global batch size: 256 | lm loss: 2.145321E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.625 | TFLOPs: 20.18 | +31: iteration 27790/ 39672 | consumed samples: 7114240 | consumed tokens: 14569963520 | elapsed time per iteration (s): 0.73 | learning rate: 5.768E-05 | global batch size: 256 | lm loss: 2.104552E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.210 | TFLOPs: 21.19 | +31: iteration 27800/ 39672 | consumed samples: 7116800 | consumed tokens: 14575206400 | elapsed time per iteration (s): 0.78 | learning rate: 5.762E-05 | global batch size: 256 | lm loss: 2.102839E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.733 | TFLOPs: 19.77 | +31: iteration 27810/ 39672 | consumed samples: 7119360 | consumed tokens: 14580449280 | elapsed time per iteration (s): 0.78 | learning rate: 5.757E-05 | global batch size: 256 | lm loss: 2.098735E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.370 | TFLOPs: 19.74 | +31: iteration 27820/ 39672 | consumed samples: 7121920 | consumed tokens: 14585692160 | elapsed time per iteration (s): 0.78 | learning rate: 5.751E-05 | global batch size: 256 | lm loss: 2.101138E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.349 | TFLOPs: 19.80 | +31: iteration 27830/ 39672 | consumed samples: 7124480 | consumed tokens: 14590935040 | elapsed time per iteration (s): 0.78 | learning rate: 5.745E-05 | global batch size: 256 | lm loss: 2.123007E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.159 | TFLOPs: 19.97 | +31: iteration 27840/ 39672 | consumed samples: 7127040 | consumed tokens: 14596177920 | elapsed time per iteration (s): 0.74 | learning rate: 5.739E-05 | global batch size: 256 | lm loss: 2.126737E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.389 | TFLOPs: 21.02 | +31: iteration 27850/ 39672 | consumed samples: 7129600 | consumed tokens: 14601420800 | elapsed time per iteration (s): 0.78 | learning rate: 5.733E-05 | global batch size: 256 | lm loss: 2.133043E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.382 | TFLOPs: 19.87 | +31: iteration 27860/ 39672 | consumed samples: 7132160 | consumed tokens: 14606663680 | elapsed time per iteration (s): 0.73 | learning rate: 5.727E-05 | global batch size: 256 | lm loss: 2.135478E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.190 | TFLOPs: 21.19 | +31: iteration 27870/ 39672 | consumed samples: 7134720 | consumed tokens: 14611906560 | elapsed time per iteration (s): 0.80 | learning rate: 5.722E-05 | global batch size: 256 | lm loss: 2.093870E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.301 | TFLOPs: 19.44 | +31: iteration 27880/ 39672 | consumed samples: 7137280 | consumed tokens: 14617149440 | elapsed time per iteration (s): 0.74 | learning rate: 5.716E-05 | global batch size: 256 | lm loss: 2.140697E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.023 | TFLOPs: 21.05 | +31: iteration 27890/ 39672 | consumed samples: 7139840 | consumed tokens: 14622392320 | elapsed time per iteration (s): 0.74 | learning rate: 5.710E-05 | global batch size: 256 | lm loss: 2.092245E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.300 | TFLOPs: 20.89 | +31: iteration 27900/ 39672 | consumed samples: 7142400 | consumed tokens: 14627635200 | elapsed time per iteration (s): 0.79 | learning rate: 5.704E-05 | global batch size: 256 | lm loss: 2.068242E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.007 | TFLOPs: 19.60 | +31: iteration 27910/ 39672 | consumed samples: 7144960 | consumed tokens: 14632878080 | elapsed time per iteration (s): 0.74 | learning rate: 5.698E-05 | global batch size: 256 | lm loss: 2.108450E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.793 | TFLOPs: 20.80 | +31: iteration 27920/ 39672 | consumed samples: 7147520 | consumed tokens: 14638120960 | elapsed time per iteration (s): 0.76 | learning rate: 5.692E-05 | global batch size: 256 | lm loss: 2.089822E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.015 | TFLOPs: 20.27 | +31: iteration 27930/ 39672 | consumed samples: 7150080 | consumed tokens: 14643363840 | elapsed time per iteration (s): 0.76 | learning rate: 5.687E-05 | global batch size: 256 | lm loss: 2.104006E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.387 | TFLOPs: 20.41 | +31: iteration 27940/ 39672 | consumed samples: 7152640 | consumed tokens: 14648606720 | elapsed time per iteration (s): 0.81 | learning rate: 5.681E-05 | global batch size: 256 | lm loss: 2.155347E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.281 | TFLOPs: 19.01 | +31: iteration 27950/ 39672 | consumed samples: 7155200 | consumed tokens: 14653849600 | elapsed time per iteration (s): 0.77 | learning rate: 5.675E-05 | global batch size: 256 | lm loss: 2.114949E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.207 | TFLOPs: 20.10 | +31: iteration 27960/ 39672 | consumed samples: 7157760 | consumed tokens: 14659092480 | elapsed time per iteration (s): 0.79 | learning rate: 5.669E-05 | global batch size: 256 | lm loss: 2.106182E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.607 | TFLOPs: 19.70 | +31: iteration 27970/ 39672 | consumed samples: 7160320 | consumed tokens: 14664335360 | elapsed time per iteration (s): 0.77 | learning rate: 5.663E-05 | global batch size: 256 | lm loss: 2.108998E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.842 | TFLOPs: 20.02 | +31: iteration 27980/ 39672 | consumed samples: 7162880 | consumed tokens: 14669578240 | elapsed time per iteration (s): 0.78 | learning rate: 5.658E-05 | global batch size: 256 | lm loss: 2.126044E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.924 | TFLOPs: 19.96 | +31: iteration 27990/ 39672 | consumed samples: 7165440 | consumed tokens: 14674821120 | elapsed time per iteration (s): 0.82 | learning rate: 5.652E-05 | global batch size: 256 | lm loss: 2.110426E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.825 | TFLOPs: 18.86 | + 0: [2022-11-30 15:23:56,606] [INFO] [logging.py:68:log_dist] [Rank 0] step=28000, skipped=0, lr=[5.6460831263507936e-05, 5.6460831263507936e-05, 5.6460831263507936e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 28000/ 39672 | consumed samples: 7168000 | consumed tokens: 14680064000 | elapsed time per iteration (s): 0.83 | learning rate: 5.646E-05 | global batch size: 256 | lm loss: 2.111617E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.643 | TFLOPs: 18.61 | + 0: steps: 28000 loss: 2.1570 iter time (s): 0.774 samples/sec: 330.805 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 28000 | lm loss value: 2.118785E+00 | lm loss PPL: 8.321022E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 28010/ 39672 | consumed samples: 7170560 | consumed tokens: 14685306880 | elapsed time per iteration (s): 0.82 | learning rate: 5.640E-05 | global batch size: 256 | lm loss: 2.132759E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.716 | TFLOPs: 18.86 | +31: iteration 28020/ 39672 | consumed samples: 7173120 | consumed tokens: 14690549760 | elapsed time per iteration (s): 0.81 | learning rate: 5.635E-05 | global batch size: 256 | lm loss: 2.080759E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.726 | TFLOPs: 19.22 | +31: iteration 28030/ 39672 | consumed samples: 7175680 | consumed tokens: 14695792640 | elapsed time per iteration (s): 0.78 | learning rate: 5.629E-05 | global batch size: 256 | lm loss: 2.120311E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.582 | TFLOPs: 19.88 | +31: iteration 28040/ 39672 | consumed samples: 7178240 | consumed tokens: 14701035520 | elapsed time per iteration (s): 0.85 | learning rate: 5.623E-05 | global batch size: 256 | lm loss: 2.117534E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.299 | TFLOPs: 18.29 | +31: iteration 28050/ 39672 | consumed samples: 7180800 | consumed tokens: 14706278400 | elapsed time per iteration (s): 0.84 | learning rate: 5.617E-05 | global batch size: 256 | lm loss: 2.088533E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.281 | TFLOPs: 18.41 | +31: iteration 28060/ 39672 | consumed samples: 7183360 | consumed tokens: 14711521280 | elapsed time per iteration (s): 0.84 | learning rate: 5.611E-05 | global batch size: 256 | lm loss: 2.100278E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.034 | TFLOPs: 18.39 | +31: iteration 28070/ 39672 | consumed samples: 7185920 | consumed tokens: 14716764160 | elapsed time per iteration (s): 0.76 | learning rate: 5.606E-05 | global batch size: 256 | lm loss: 2.139976E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.304 | TFLOPs: 20.29 | +31: iteration 28080/ 39672 | consumed samples: 7188480 | consumed tokens: 14722007040 | elapsed time per iteration (s): 0.77 | learning rate: 5.600E-05 | global batch size: 256 | lm loss: 2.105580E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.811 | TFLOPs: 20.07 | +31: iteration 28090/ 39672 | consumed samples: 7191040 | consumed tokens: 14727249920 | elapsed time per iteration (s): 0.74 | learning rate: 5.594E-05 | global batch size: 256 | lm loss: 2.109789E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.223 | TFLOPs: 21.01 | +31: iteration 28100/ 39672 | consumed samples: 7193600 | consumed tokens: 14732492800 | elapsed time per iteration (s): 0.84 | learning rate: 5.588E-05 | global batch size: 256 | lm loss: 2.126315E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.980 | TFLOPs: 18.51 | +31: iteration 28110/ 39672 | consumed samples: 7196160 | consumed tokens: 14737735680 | elapsed time per iteration (s): 0.78 | learning rate: 5.583E-05 | global batch size: 256 | lm loss: 2.110534E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.300 | TFLOPs: 19.74 | +31: iteration 28120/ 39672 | consumed samples: 7198720 | consumed tokens: 14742978560 | elapsed time per iteration (s): 0.77 | learning rate: 5.577E-05 | global batch size: 256 | lm loss: 2.108717E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.038 | TFLOPs: 20.15 | +31: iteration 28130/ 39672 | consumed samples: 7201280 | consumed tokens: 14748221440 | elapsed time per iteration (s): 0.72 | learning rate: 5.571E-05 | global batch size: 256 | lm loss: 2.135060E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.636 | TFLOPs: 21.39 | +31: iteration 28140/ 39672 | consumed samples: 7203840 | consumed tokens: 14753464320 | elapsed time per iteration (s): 0.76 | learning rate: 5.565E-05 | global batch size: 256 | lm loss: 2.124542E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.502 | TFLOPs: 20.30 | +31: iteration 28150/ 39672 | consumed samples: 7206400 | consumed tokens: 14758707200 | elapsed time per iteration (s): 0.77 | learning rate: 5.560E-05 | global batch size: 256 | lm loss: 2.118558E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.171 | TFLOPs: 20.10 | +31: iteration 28160/ 39672 | consumed samples: 7208960 | consumed tokens: 14763950080 | elapsed time per iteration (s): 0.77 | learning rate: 5.554E-05 | global batch size: 256 | lm loss: 2.088296E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.905 | TFLOPs: 20.02 | +31: iteration 28170/ 39672 | consumed samples: 7211520 | consumed tokens: 14769192960 | elapsed time per iteration (s): 0.81 | learning rate: 5.548E-05 | global batch size: 256 | lm loss: 2.104167E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.215 | TFLOPs: 19.01 | +31: iteration 28180/ 39672 | consumed samples: 7214080 | consumed tokens: 14774435840 | elapsed time per iteration (s): 0.82 | learning rate: 5.542E-05 | global batch size: 256 | lm loss: 2.090726E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.377 | TFLOPs: 18.96 | +31: iteration 28190/ 39672 | consumed samples: 7216640 | consumed tokens: 14779678720 | elapsed time per iteration (s): 0.83 | learning rate: 5.537E-05 | global batch size: 256 | lm loss: 2.113609E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.966 | TFLOPs: 18.63 | +31: iteration 28200/ 39672 | consumed samples: 7219200 | consumed tokens: 14784921600 | elapsed time per iteration (s): 0.81 | learning rate: 5.531E-05 | global batch size: 256 | lm loss: 2.078681E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.063 | TFLOPs: 19.18 | +31: iteration 28210/ 39672 | consumed samples: 7221760 | consumed tokens: 14790164480 | elapsed time per iteration (s): 0.80 | learning rate: 5.525E-05 | global batch size: 256 | lm loss: 2.094503E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.970 | TFLOPs: 19.48 | +31: iteration 28220/ 39672 | consumed samples: 7224320 | consumed tokens: 14795407360 | elapsed time per iteration (s): 0.84 | learning rate: 5.520E-05 | global batch size: 256 | lm loss: 2.126567E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.687 | TFLOPs: 18.49 | +31: iteration 28230/ 39672 | consumed samples: 7226880 | consumed tokens: 14800650240 | elapsed time per iteration (s): 0.82 | learning rate: 5.514E-05 | global batch size: 256 | lm loss: 2.098689E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.830 | TFLOPs: 18.80 | +31: iteration 28240/ 39672 | consumed samples: 7229440 | consumed tokens: 14805893120 | elapsed time per iteration (s): 0.80 | learning rate: 5.508E-05 | global batch size: 256 | lm loss: 2.100092E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.627 | TFLOPs: 19.46 | +31: iteration 28250/ 39672 | consumed samples: 7232000 | consumed tokens: 14811136000 | elapsed time per iteration (s): 0.82 | learning rate: 5.502E-05 | global batch size: 256 | lm loss: 2.107866E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.447 | TFLOPs: 18.90 | +31: iteration 28260/ 39672 | consumed samples: 7234560 | consumed tokens: 14816378880 | elapsed time per iteration (s): 0.79 | learning rate: 5.497E-05 | global batch size: 256 | lm loss: 2.103462E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.786 | TFLOPs: 19.53 | +31: iteration 28270/ 39672 | consumed samples: 7237120 | consumed tokens: 14821621760 | elapsed time per iteration (s): 0.81 | learning rate: 5.491E-05 | global batch size: 256 | lm loss: 2.091979E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.518 | TFLOPs: 19.03 | +31: iteration 28280/ 39672 | consumed samples: 7239680 | consumed tokens: 14826864640 | elapsed time per iteration (s): 0.82 | learning rate: 5.485E-05 | global batch size: 256 | lm loss: 2.114904E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.950 | TFLOPs: 18.99 | +31: iteration 28290/ 39672 | consumed samples: 7242240 | consumed tokens: 14832107520 | elapsed time per iteration (s): 0.83 | learning rate: 5.480E-05 | global batch size: 256 | lm loss: 2.121908E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.775 | TFLOPs: 18.68 | +31: iteration 28300/ 39672 | consumed samples: 7244800 | consumed tokens: 14837350400 | elapsed time per iteration (s): 0.82 | learning rate: 5.474E-05 | global batch size: 256 | lm loss: 2.103893E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.134 | TFLOPs: 18.94 | +31: iteration 28310/ 39672 | consumed samples: 7247360 | consumed tokens: 14842593280 | elapsed time per iteration (s): 0.82 | learning rate: 5.468E-05 | global batch size: 256 | lm loss: 2.135666E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.183 | TFLOPs: 18.89 | +31: iteration 28320/ 39672 | consumed samples: 7249920 | consumed tokens: 14847836160 | elapsed time per iteration (s): 0.81 | learning rate: 5.463E-05 | global batch size: 256 | lm loss: 2.161816E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.368 | TFLOPs: 19.02 | +31: iteration 28330/ 39672 | consumed samples: 7252480 | consumed tokens: 14853079040 | elapsed time per iteration (s): 0.79 | learning rate: 5.457E-05 | global batch size: 256 | lm loss: 2.131063E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.549 | TFLOPs: 19.51 | +31: iteration 28340/ 39672 | consumed samples: 7255040 | consumed tokens: 14858321920 | elapsed time per iteration (s): 0.84 | learning rate: 5.451E-05 | global batch size: 256 | lm loss: 2.115196E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.373 | TFLOPs: 18.47 | +31: iteration 28350/ 39672 | consumed samples: 7257600 | consumed tokens: 14863564800 | elapsed time per iteration (s): 0.85 | learning rate: 5.446E-05 | global batch size: 256 | lm loss: 2.098066E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.376 | TFLOPs: 18.29 | +31: iteration 28360/ 39672 | consumed samples: 7260160 | consumed tokens: 14868807680 | elapsed time per iteration (s): 0.83 | learning rate: 5.440E-05 | global batch size: 256 | lm loss: 2.118128E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.023 | TFLOPs: 18.63 | +31: iteration 28370/ 39672 | consumed samples: 7262720 | consumed tokens: 14874050560 | elapsed time per iteration (s): 0.85 | learning rate: 5.434E-05 | global batch size: 256 | lm loss: 2.124954E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.229 | TFLOPs: 18.22 | +31: iteration 28380/ 39672 | consumed samples: 7265280 | consumed tokens: 14879293440 | elapsed time per iteration (s): 0.78 | learning rate: 5.429E-05 | global batch size: 256 | lm loss: 2.091312E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.679 | TFLOPs: 19.88 | +31: iteration 28390/ 39672 | consumed samples: 7267840 | consumed tokens: 14884536320 | elapsed time per iteration (s): 0.80 | learning rate: 5.423E-05 | global batch size: 256 | lm loss: 2.102567E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.722 | TFLOPs: 19.34 | +31: iteration 28400/ 39672 | consumed samples: 7270400 | consumed tokens: 14889779200 | elapsed time per iteration (s): 0.73 | learning rate: 5.417E-05 | global batch size: 256 | lm loss: 2.128333E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.705 | TFLOPs: 21.28 | +31: iteration 28410/ 39672 | consumed samples: 7272960 | consumed tokens: 14895022080 | elapsed time per iteration (s): 0.79 | learning rate: 5.412E-05 | global batch size: 256 | lm loss: 2.107796E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.551 | TFLOPs: 19.69 | +31: iteration 28420/ 39672 | consumed samples: 7275520 | consumed tokens: 14900264960 | elapsed time per iteration (s): 0.76 | learning rate: 5.406E-05 | global batch size: 256 | lm loss: 2.135688E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.692 | TFLOPs: 20.49 | +31: iteration 28430/ 39672 | consumed samples: 7278080 | consumed tokens: 14905507840 | elapsed time per iteration (s): 0.82 | learning rate: 5.400E-05 | global batch size: 256 | lm loss: 2.084519E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.637 | TFLOPs: 18.91 | +31: iteration 28440/ 39672 | consumed samples: 7280640 | consumed tokens: 14910750720 | elapsed time per iteration (s): 0.77 | learning rate: 5.395E-05 | global batch size: 256 | lm loss: 2.099052E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.890 | TFLOPs: 20.20 | +31: iteration 28450/ 39672 | consumed samples: 7283200 | consumed tokens: 14915993600 | elapsed time per iteration (s): 0.77 | learning rate: 5.389E-05 | global batch size: 256 | lm loss: 2.084816E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.619 | TFLOPs: 20.06 | +31: iteration 28460/ 39672 | consumed samples: 7285760 | consumed tokens: 14921236480 | elapsed time per iteration (s): 0.80 | learning rate: 5.384E-05 | global batch size: 256 | lm loss: 2.104869E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.405 | TFLOPs: 19.26 | +31: iteration 28470/ 39672 | consumed samples: 7288320 | consumed tokens: 14926479360 | elapsed time per iteration (s): 0.79 | learning rate: 5.378E-05 | global batch size: 256 | lm loss: 2.071845E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.001 | TFLOPs: 19.66 | +31: iteration 28480/ 39672 | consumed samples: 7290880 | consumed tokens: 14931722240 | elapsed time per iteration (s): 0.76 | learning rate: 5.372E-05 | global batch size: 256 | lm loss: 2.113745E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.141 | TFLOPs: 20.28 | +31: iteration 28490/ 39672 | consumed samples: 7293440 | consumed tokens: 14936965120 | elapsed time per iteration (s): 0.74 | learning rate: 5.367E-05 | global batch size: 256 | lm loss: 2.111688E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.731 | TFLOPs: 21.04 | +31: iteration 28500/ 39672 | consumed samples: 7296000 | consumed tokens: 14942208000 | elapsed time per iteration (s): 0.79 | learning rate: 5.361E-05 | global batch size: 256 | lm loss: 2.120564E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.753 | TFLOPs: 19.71 | +31: iteration 28510/ 39672 | consumed samples: 7298560 | consumed tokens: 14947450880 | elapsed time per iteration (s): 0.73 | learning rate: 5.356E-05 | global batch size: 256 | lm loss: 2.114806E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.880 | TFLOPs: 21.23 | +31: iteration 28520/ 39672 | consumed samples: 7301120 | consumed tokens: 14952693760 | elapsed time per iteration (s): 0.77 | learning rate: 5.350E-05 | global batch size: 256 | lm loss: 2.127457E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.583 | TFLOPs: 20.00 | +31: iteration 28530/ 39672 | consumed samples: 7303680 | consumed tokens: 14957936640 | elapsed time per iteration (s): 0.77 | learning rate: 5.344E-05 | global batch size: 256 | lm loss: 2.092952E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.063 | TFLOPs: 20.15 | +31: iteration 28540/ 39672 | consumed samples: 7306240 | consumed tokens: 14963179520 | elapsed time per iteration (s): 0.79 | learning rate: 5.339E-05 | global batch size: 256 | lm loss: 2.118439E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.371 | TFLOPs: 19.50 | +31: iteration 28550/ 39672 | consumed samples: 7308800 | consumed tokens: 14968422400 | elapsed time per iteration (s): 0.83 | learning rate: 5.333E-05 | global batch size: 256 | lm loss: 2.116203E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.910 | TFLOPs: 18.63 | +31: iteration 28560/ 39672 | consumed samples: 7311360 | consumed tokens: 14973665280 | elapsed time per iteration (s): 0.79 | learning rate: 5.328E-05 | global batch size: 256 | lm loss: 2.115398E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.475 | TFLOPs: 19.69 | +31: iteration 28570/ 39672 | consumed samples: 7313920 | consumed tokens: 14978908160 | elapsed time per iteration (s): 0.80 | learning rate: 5.322E-05 | global batch size: 256 | lm loss: 2.089394E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.094 | TFLOPs: 19.43 | +31: iteration 28580/ 39672 | consumed samples: 7316480 | consumed tokens: 14984151040 | elapsed time per iteration (s): 0.79 | learning rate: 5.316E-05 | global batch size: 256 | lm loss: 2.111745E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.770 | TFLOPs: 19.53 | +31: iteration 28590/ 39672 | consumed samples: 7319040 | consumed tokens: 14989393920 | elapsed time per iteration (s): 0.81 | learning rate: 5.311E-05 | global batch size: 256 | lm loss: 2.102625E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.539 | TFLOPs: 19.21 | +31: iteration 28600/ 39672 | consumed samples: 7321600 | consumed tokens: 14994636800 | elapsed time per iteration (s): 0.80 | learning rate: 5.305E-05 | global batch size: 256 | lm loss: 2.122839E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.442 | TFLOPs: 19.33 | +31: iteration 28610/ 39672 | consumed samples: 7324160 | consumed tokens: 14999879680 | elapsed time per iteration (s): 0.85 | learning rate: 5.300E-05 | global batch size: 256 | lm loss: 2.108884E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.593 | TFLOPs: 18.31 | +31: iteration 28620/ 39672 | consumed samples: 7326720 | consumed tokens: 15005122560 | elapsed time per iteration (s): 0.81 | learning rate: 5.294E-05 | global batch size: 256 | lm loss: 2.104930E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.699 | TFLOPs: 19.04 | +31: iteration 28630/ 39672 | consumed samples: 7329280 | consumed tokens: 15010365440 | elapsed time per iteration (s): 0.84 | learning rate: 5.288E-05 | global batch size: 256 | lm loss: 2.107479E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.899 | TFLOPs: 18.45 | +31: iteration 28640/ 39672 | consumed samples: 7331840 | consumed tokens: 15015608320 | elapsed time per iteration (s): 0.82 | learning rate: 5.283E-05 | global batch size: 256 | lm loss: 2.120598E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.647 | TFLOPs: 18.79 | +31: iteration 28650/ 39672 | consumed samples: 7334400 | consumed tokens: 15020851200 | elapsed time per iteration (s): 0.79 | learning rate: 5.277E-05 | global batch size: 256 | lm loss: 2.094754E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.488 | TFLOPs: 19.63 | +31: iteration 28660/ 39672 | consumed samples: 7336960 | consumed tokens: 15026094080 | elapsed time per iteration (s): 0.79 | learning rate: 5.272E-05 | global batch size: 256 | lm loss: 2.122619E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.525 | TFLOPs: 19.57 | +31: iteration 28670/ 39672 | consumed samples: 7339520 | consumed tokens: 15031336960 | elapsed time per iteration (s): 0.83 | learning rate: 5.266E-05 | global batch size: 256 | lm loss: 2.105980E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.138 | TFLOPs: 18.70 | +31: iteration 28680/ 39672 | consumed samples: 7342080 | consumed tokens: 15036579840 | elapsed time per iteration (s): 0.78 | learning rate: 5.261E-05 | global batch size: 256 | lm loss: 2.117306E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.534 | TFLOPs: 19.81 | +31: iteration 28690/ 39672 | consumed samples: 7344640 | consumed tokens: 15041822720 | elapsed time per iteration (s): 0.78 | learning rate: 5.255E-05 | global batch size: 256 | lm loss: 2.096264E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.246 | TFLOPs: 19.92 | +31: iteration 28700/ 39672 | consumed samples: 7347200 | consumed tokens: 15047065600 | elapsed time per iteration (s): 0.81 | learning rate: 5.250E-05 | global batch size: 256 | lm loss: 2.123184E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.614 | TFLOPs: 19.03 | +31: iteration 28710/ 39672 | consumed samples: 7349760 | consumed tokens: 15052308480 | elapsed time per iteration (s): 0.82 | learning rate: 5.244E-05 | global batch size: 256 | lm loss: 2.096629E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.280 | TFLOPs: 18.95 | +31: iteration 28720/ 39672 | consumed samples: 7352320 | consumed tokens: 15057551360 | elapsed time per iteration (s): 0.77 | learning rate: 5.239E-05 | global batch size: 256 | lm loss: 2.117327E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.470 | TFLOPs: 20.17 | +31: iteration 28730/ 39672 | consumed samples: 7354880 | consumed tokens: 15062794240 | elapsed time per iteration (s): 0.78 | learning rate: 5.233E-05 | global batch size: 256 | lm loss: 2.127707E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.737 | TFLOPs: 19.89 | +31: iteration 28740/ 39672 | consumed samples: 7357440 | consumed tokens: 15068037120 | elapsed time per iteration (s): 0.75 | learning rate: 5.228E-05 | global batch size: 256 | lm loss: 2.136498E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.445 | TFLOPs: 20.66 | +31: iteration 28750/ 39672 | consumed samples: 7360000 | consumed tokens: 15073280000 | elapsed time per iteration (s): 0.75 | learning rate: 5.222E-05 | global batch size: 256 | lm loss: 2.131546E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.868 | TFLOPs: 20.68 | +31: iteration 28760/ 39672 | consumed samples: 7362560 | consumed tokens: 15078522880 | elapsed time per iteration (s): 0.74 | learning rate: 5.216E-05 | global batch size: 256 | lm loss: 2.113828E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.803 | TFLOPs: 20.86 | +31: iteration 28770/ 39672 | consumed samples: 7365120 | consumed tokens: 15083765760 | elapsed time per iteration (s): 0.77 | learning rate: 5.211E-05 | global batch size: 256 | lm loss: 2.109547E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.280 | TFLOPs: 20.10 | +31: iteration 28780/ 39672 | consumed samples: 7367680 | consumed tokens: 15089008640 | elapsed time per iteration (s): 0.76 | learning rate: 5.205E-05 | global batch size: 256 | lm loss: 2.116825E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.073 | TFLOPs: 20.39 | +31: iteration 28790/ 39672 | consumed samples: 7370240 | consumed tokens: 15094251520 | elapsed time per iteration (s): 0.84 | learning rate: 5.200E-05 | global batch size: 256 | lm loss: 2.106737E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.933 | TFLOPs: 18.45 | +31: iteration 28800/ 39672 | consumed samples: 7372800 | consumed tokens: 15099494400 | elapsed time per iteration (s): 0.82 | learning rate: 5.194E-05 | global batch size: 256 | lm loss: 2.112263E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.775 | TFLOPs: 18.80 | +31: iteration 28810/ 39672 | consumed samples: 7375360 | consumed tokens: 15104737280 | elapsed time per iteration (s): 0.82 | learning rate: 5.189E-05 | global batch size: 256 | lm loss: 2.098040E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.200 | TFLOPs: 18.89 | +31: iteration 28820/ 39672 | consumed samples: 7377920 | consumed tokens: 15109980160 | elapsed time per iteration (s): 0.79 | learning rate: 5.183E-05 | global batch size: 256 | lm loss: 2.088026E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.662 | TFLOPs: 19.52 | +31: iteration 28830/ 39672 | consumed samples: 7380480 | consumed tokens: 15115223040 | elapsed time per iteration (s): 0.79 | learning rate: 5.178E-05 | global batch size: 256 | lm loss: 2.114794E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.940 | TFLOPs: 19.72 | +31: iteration 28840/ 39672 | consumed samples: 7383040 | consumed tokens: 15120465920 | elapsed time per iteration (s): 0.82 | learning rate: 5.172E-05 | global batch size: 256 | lm loss: 2.091998E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.804 | TFLOPs: 18.98 | +31: iteration 28850/ 39672 | consumed samples: 7385600 | consumed tokens: 15125708800 | elapsed time per iteration (s): 0.81 | learning rate: 5.167E-05 | global batch size: 256 | lm loss: 2.120156E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.449 | TFLOPs: 19.20 | +31: iteration 28860/ 39672 | consumed samples: 7388160 | consumed tokens: 15130951680 | elapsed time per iteration (s): 0.79 | learning rate: 5.161E-05 | global batch size: 256 | lm loss: 2.104155E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.005 | TFLOPs: 19.60 | +31: iteration 28870/ 39672 | consumed samples: 7390720 | consumed tokens: 15136194560 | elapsed time per iteration (s): 0.82 | learning rate: 5.156E-05 | global batch size: 256 | lm loss: 2.103322E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.188 | TFLOPs: 18.95 | +31: iteration 28880/ 39672 | consumed samples: 7393280 | consumed tokens: 15141437440 | elapsed time per iteration (s): 0.81 | learning rate: 5.151E-05 | global batch size: 256 | lm loss: 2.116224E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.012 | TFLOPs: 19.18 | +31: iteration 28890/ 39672 | consumed samples: 7395840 | consumed tokens: 15146680320 | elapsed time per iteration (s): 0.80 | learning rate: 5.145E-05 | global batch size: 256 | lm loss: 2.116070E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.497 | TFLOPs: 19.33 | +31: iteration 28900/ 39672 | consumed samples: 7398400 | consumed tokens: 15151923200 | elapsed time per iteration (s): 0.79 | learning rate: 5.140E-05 | global batch size: 256 | lm loss: 2.111617E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.114 | TFLOPs: 19.49 | +31: iteration 28910/ 39672 | consumed samples: 7400960 | consumed tokens: 15157166080 | elapsed time per iteration (s): 0.79 | learning rate: 5.134E-05 | global batch size: 256 | lm loss: 2.116196E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.768 | TFLOPs: 19.53 | +31: iteration 28920/ 39672 | consumed samples: 7403520 | consumed tokens: 15162408960 | elapsed time per iteration (s): 0.79 | learning rate: 5.129E-05 | global batch size: 256 | lm loss: 2.124849E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.556 | TFLOPs: 19.57 | +31: iteration 28930/ 39672 | consumed samples: 7406080 | consumed tokens: 15167651840 | elapsed time per iteration (s): 0.81 | learning rate: 5.123E-05 | global batch size: 256 | lm loss: 2.107156E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.816 | TFLOPs: 19.17 | +31: iteration 28940/ 39672 | consumed samples: 7408640 | consumed tokens: 15172894720 | elapsed time per iteration (s): 0.85 | learning rate: 5.118E-05 | global batch size: 256 | lm loss: 2.128744E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.745 | TFLOPs: 18.19 | +31: iteration 28950/ 39672 | consumed samples: 7411200 | consumed tokens: 15178137600 | elapsed time per iteration (s): 0.77 | learning rate: 5.112E-05 | global batch size: 256 | lm loss: 2.126754E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.326 | TFLOPs: 20.10 | +31: iteration 28960/ 39672 | consumed samples: 7413760 | consumed tokens: 15183380480 | elapsed time per iteration (s): 0.75 | learning rate: 5.107E-05 | global batch size: 256 | lm loss: 2.082209E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.361 | TFLOPs: 20.59 | +31: iteration 28970/ 39672 | consumed samples: 7416320 | consumed tokens: 15188623360 | elapsed time per iteration (s): 0.72 | learning rate: 5.101E-05 | global batch size: 256 | lm loss: 2.143152E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.719 | TFLOPs: 21.58 | +31: iteration 28980/ 39672 | consumed samples: 7418880 | consumed tokens: 15193866240 | elapsed time per iteration (s): 0.76 | learning rate: 5.096E-05 | global batch size: 256 | lm loss: 2.137266E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.153 | TFLOPs: 20.46 | +31: iteration 28990/ 39672 | consumed samples: 7421440 | consumed tokens: 15199109120 | elapsed time per iteration (s): 0.75 | learning rate: 5.091E-05 | global batch size: 256 | lm loss: 2.115802E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.867 | TFLOPs: 20.74 | +31: iteration 29000/ 39672 | consumed samples: 7424000 | consumed tokens: 15204352000 | elapsed time per iteration (s): 0.76 | learning rate: 5.085E-05 | global batch size: 256 | lm loss: 2.092920E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.518 | TFLOPs: 20.30 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 29000 | lm loss value: 2.163503E+00 | lm loss PPL: 8.701567E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 29010/ 39672 | consumed samples: 7426560 | consumed tokens: 15209594880 | elapsed time per iteration (s): 0.79 | learning rate: 5.080E-05 | global batch size: 256 | lm loss: 2.069969E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.043 | TFLOPs: 19.72 | +31: iteration 29020/ 39672 | consumed samples: 7429120 | consumed tokens: 15214837760 | elapsed time per iteration (s): 0.80 | learning rate: 5.074E-05 | global batch size: 256 | lm loss: 2.114677E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.831 | TFLOPs: 19.47 | +31: iteration 29030/ 39672 | consumed samples: 7431680 | consumed tokens: 15220080640 | elapsed time per iteration (s): 0.75 | learning rate: 5.069E-05 | global batch size: 256 | lm loss: 2.100911E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.500 | TFLOPs: 20.78 | +31: iteration 29040/ 39672 | consumed samples: 7434240 | consumed tokens: 15225323520 | elapsed time per iteration (s): 0.77 | learning rate: 5.063E-05 | global batch size: 256 | lm loss: 2.093721E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.226 | TFLOPs: 20.10 | +31: iteration 29050/ 39672 | consumed samples: 7436800 | consumed tokens: 15230566400 | elapsed time per iteration (s): 0.76 | learning rate: 5.058E-05 | global batch size: 256 | lm loss: 2.115564E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.972 | TFLOPs: 20.33 | +31: iteration 29060/ 39672 | consumed samples: 7439360 | consumed tokens: 15235809280 | elapsed time per iteration (s): 0.75 | learning rate: 5.053E-05 | global batch size: 256 | lm loss: 2.117979E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.487 | TFLOPs: 20.54 | +31: iteration 29070/ 39672 | consumed samples: 7441920 | consumed tokens: 15241052160 | elapsed time per iteration (s): 0.78 | learning rate: 5.047E-05 | global batch size: 256 | lm loss: 2.093438E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.092 | TFLOPs: 19.91 | +31: iteration 29080/ 39672 | consumed samples: 7444480 | consumed tokens: 15246295040 | elapsed time per iteration (s): 0.79 | learning rate: 5.042E-05 | global batch size: 256 | lm loss: 2.126827E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.364 | TFLOPs: 19.56 | +31: iteration 29090/ 39672 | consumed samples: 7447040 | consumed tokens: 15251537920 | elapsed time per iteration (s): 0.80 | learning rate: 5.036E-05 | global batch size: 256 | lm loss: 2.112293E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.682 | TFLOPs: 19.40 | +31: iteration 29100/ 39672 | consumed samples: 7449600 | consumed tokens: 15256780800 | elapsed time per iteration (s): 0.81 | learning rate: 5.031E-05 | global batch size: 256 | lm loss: 2.081059E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.244 | TFLOPs: 19.19 | +31: iteration 29110/ 39672 | consumed samples: 7452160 | consumed tokens: 15262023680 | elapsed time per iteration (s): 0.80 | learning rate: 5.026E-05 | global batch size: 256 | lm loss: 2.109643E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.678 | TFLOPs: 19.46 | +31: iteration 29120/ 39672 | consumed samples: 7454720 | consumed tokens: 15267266560 | elapsed time per iteration (s): 0.83 | learning rate: 5.020E-05 | global batch size: 256 | lm loss: 2.088638E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.209 | TFLOPs: 18.77 | +31: iteration 29130/ 39672 | consumed samples: 7457280 | consumed tokens: 15272509440 | elapsed time per iteration (s): 0.76 | learning rate: 5.015E-05 | global batch size: 256 | lm loss: 2.106106E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.396 | TFLOPs: 20.41 | +31: iteration 29140/ 39672 | consumed samples: 7459840 | consumed tokens: 15277752320 | elapsed time per iteration (s): 0.81 | learning rate: 5.010E-05 | global batch size: 256 | lm loss: 2.094615E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.493 | TFLOPs: 19.15 | +31: iteration 29150/ 39672 | consumed samples: 7462400 | consumed tokens: 15282995200 | elapsed time per iteration (s): 0.80 | learning rate: 5.004E-05 | global batch size: 256 | lm loss: 2.119941E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.517 | TFLOPs: 19.33 | +31: iteration 29160/ 39672 | consumed samples: 7464960 | consumed tokens: 15288238080 | elapsed time per iteration (s): 0.80 | learning rate: 4.999E-05 | global batch size: 256 | lm loss: 2.099505E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.232 | TFLOPs: 19.31 | +31: iteration 29170/ 39672 | consumed samples: 7467520 | consumed tokens: 15293480960 | elapsed time per iteration (s): 0.83 | learning rate: 4.993E-05 | global batch size: 256 | lm loss: 2.093003E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.247 | TFLOPs: 18.59 | +31: iteration 29180/ 39672 | consumed samples: 7470080 | consumed tokens: 15298723840 | elapsed time per iteration (s): 0.79 | learning rate: 4.988E-05 | global batch size: 256 | lm loss: 2.117209E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.036 | TFLOPs: 19.66 | +31: iteration 29190/ 39672 | consumed samples: 7472640 | consumed tokens: 15303966720 | elapsed time per iteration (s): 0.81 | learning rate: 4.983E-05 | global batch size: 256 | lm loss: 2.103559E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.656 | TFLOPs: 19.10 | +31: iteration 29200/ 39672 | consumed samples: 7475200 | consumed tokens: 15309209600 | elapsed time per iteration (s): 0.80 | learning rate: 4.977E-05 | global batch size: 256 | lm loss: 2.063569E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.234 | TFLOPs: 19.25 | +31: iteration 29210/ 39672 | consumed samples: 7477760 | consumed tokens: 15314452480 | elapsed time per iteration (s): 0.80 | learning rate: 4.972E-05 | global batch size: 256 | lm loss: 2.125909E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.991 | TFLOPs: 19.42 | +31: iteration 29220/ 39672 | consumed samples: 7480320 | consumed tokens: 15319695360 | elapsed time per iteration (s): 0.80 | learning rate: 4.967E-05 | global batch size: 256 | lm loss: 2.108716E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.572 | TFLOPs: 19.45 | +31: iteration 29230/ 39672 | consumed samples: 7482880 | consumed tokens: 15324938240 | elapsed time per iteration (s): 0.76 | learning rate: 4.961E-05 | global batch size: 256 | lm loss: 2.079873E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.942 | TFLOPs: 20.32 | +31: iteration 29240/ 39672 | consumed samples: 7485440 | consumed tokens: 15330181120 | elapsed time per iteration (s): 0.77 | learning rate: 4.956E-05 | global batch size: 256 | lm loss: 2.101117E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.935 | TFLOPs: 20.08 | +31: iteration 29250/ 39672 | consumed samples: 7488000 | consumed tokens: 15335424000 | elapsed time per iteration (s): 0.80 | learning rate: 4.951E-05 | global batch size: 256 | lm loss: 2.081645E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.807 | TFLOPs: 19.47 | +31: iteration 29260/ 39672 | consumed samples: 7490560 | consumed tokens: 15340666880 | elapsed time per iteration (s): 0.82 | learning rate: 4.945E-05 | global batch size: 256 | lm loss: 2.095928E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.351 | TFLOPs: 18.96 | +31: iteration 29270/ 39672 | consumed samples: 7493120 | consumed tokens: 15345909760 | elapsed time per iteration (s): 0.80 | learning rate: 4.940E-05 | global batch size: 256 | lm loss: 2.107265E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.020 | TFLOPs: 19.36 | +31: iteration 29280/ 39672 | consumed samples: 7495680 | consumed tokens: 15351152640 | elapsed time per iteration (s): 0.79 | learning rate: 4.935E-05 | global batch size: 256 | lm loss: 2.116052E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.912 | TFLOPs: 19.54 | +31: iteration 29290/ 39672 | consumed samples: 7498240 | consumed tokens: 15356395520 | elapsed time per iteration (s): 0.82 | learning rate: 4.929E-05 | global batch size: 256 | lm loss: 2.097923E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.968 | TFLOPs: 18.81 | +31: iteration 29300/ 39672 | consumed samples: 7500800 | consumed tokens: 15361638400 | elapsed time per iteration (s): 0.85 | learning rate: 4.924E-05 | global batch size: 256 | lm loss: 2.111639E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.581 | TFLOPs: 18.24 | +31: iteration 29310/ 39672 | consumed samples: 7503360 | consumed tokens: 15366881280 | elapsed time per iteration (s): 0.80 | learning rate: 4.919E-05 | global batch size: 256 | lm loss: 2.080594E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.947 | TFLOPs: 19.48 | +31: iteration 29320/ 39672 | consumed samples: 7505920 | consumed tokens: 15372124160 | elapsed time per iteration (s): 0.82 | learning rate: 4.913E-05 | global batch size: 256 | lm loss: 2.127750E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.849 | TFLOPs: 18.93 | +31: iteration 29330/ 39672 | consumed samples: 7508480 | consumed tokens: 15377367040 | elapsed time per iteration (s): 0.82 | learning rate: 4.908E-05 | global batch size: 256 | lm loss: 2.100991E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.758 | TFLOPs: 18.80 | +31: iteration 29340/ 39672 | consumed samples: 7511040 | consumed tokens: 15382609920 | elapsed time per iteration (s): 0.80 | learning rate: 4.903E-05 | global batch size: 256 | lm loss: 2.079993E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.439 | TFLOPs: 19.39 | +31: iteration 29350/ 39672 | consumed samples: 7513600 | consumed tokens: 15387852800 | elapsed time per iteration (s): 0.80 | learning rate: 4.898E-05 | global batch size: 256 | lm loss: 2.085973E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.936 | TFLOPs: 19.29 | +31: iteration 29360/ 39672 | consumed samples: 7516160 | consumed tokens: 15393095680 | elapsed time per iteration (s): 0.84 | learning rate: 4.892E-05 | global batch size: 256 | lm loss: 2.118010E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.595 | TFLOPs: 18.37 | +31: iteration 29370/ 39672 | consumed samples: 7518720 | consumed tokens: 15398338560 | elapsed time per iteration (s): 0.81 | learning rate: 4.887E-05 | global batch size: 256 | lm loss: 2.095792E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.878 | TFLOPs: 19.23 | +31: iteration 29380/ 39672 | consumed samples: 7521280 | consumed tokens: 15403581440 | elapsed time per iteration (s): 0.82 | learning rate: 4.882E-05 | global batch size: 256 | lm loss: 2.120152E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.492 | TFLOPs: 18.84 | +31: iteration 29390/ 39672 | consumed samples: 7523840 | consumed tokens: 15408824320 | elapsed time per iteration (s): 0.79 | learning rate: 4.876E-05 | global batch size: 256 | lm loss: 2.101455E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.397 | TFLOPs: 19.56 | +31: iteration 29400/ 39672 | consumed samples: 7526400 | consumed tokens: 15414067200 | elapsed time per iteration (s): 0.84 | learning rate: 4.871E-05 | global batch size: 256 | lm loss: 2.127641E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.742 | TFLOPs: 18.50 | +31: iteration 29410/ 39672 | consumed samples: 7528960 | consumed tokens: 15419310080 | elapsed time per iteration (s): 0.73 | learning rate: 4.866E-05 | global batch size: 256 | lm loss: 2.060852E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.843 | TFLOPs: 21.10 | +31: iteration 29420/ 39672 | consumed samples: 7531520 | consumed tokens: 15424552960 | elapsed time per iteration (s): 0.76 | learning rate: 4.861E-05 | global batch size: 256 | lm loss: 2.066035E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.320 | TFLOPs: 20.47 | +31: iteration 29430/ 39672 | consumed samples: 7534080 | consumed tokens: 15429795840 | elapsed time per iteration (s): 0.72 | learning rate: 4.855E-05 | global batch size: 256 | lm loss: 2.124592E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.074 | TFLOPs: 21.48 | +31: iteration 29440/ 39672 | consumed samples: 7536640 | consumed tokens: 15435038720 | elapsed time per iteration (s): 0.76 | learning rate: 4.850E-05 | global batch size: 256 | lm loss: 2.106566E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.381 | TFLOPs: 20.35 | +31: iteration 29450/ 39672 | consumed samples: 7539200 | consumed tokens: 15440281600 | elapsed time per iteration (s): 0.79 | learning rate: 4.845E-05 | global batch size: 256 | lm loss: 2.099090E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.011 | TFLOPs: 19.72 | +31: iteration 29460/ 39672 | consumed samples: 7541760 | consumed tokens: 15445524480 | elapsed time per iteration (s): 0.74 | learning rate: 4.840E-05 | global batch size: 256 | lm loss: 2.127319E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.944 | TFLOPs: 20.99 | +31: iteration 29470/ 39672 | consumed samples: 7544320 | consumed tokens: 15450767360 | elapsed time per iteration (s): 0.73 | learning rate: 4.834E-05 | global batch size: 256 | lm loss: 2.115888E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.320 | TFLOPs: 21.13 | +31: iteration 29480/ 39672 | consumed samples: 7546880 | consumed tokens: 15456010240 | elapsed time per iteration (s): 0.96 | learning rate: 4.829E-05 | global batch size: 256 | lm loss: 2.119056E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 265.471 | TFLOPs: 16.06 | +31: iteration 29490/ 39672 | consumed samples: 7549440 | consumed tokens: 15461253120 | elapsed time per iteration (s): 0.75 | learning rate: 4.824E-05 | global batch size: 256 | lm loss: 2.094867E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.155 | TFLOPs: 20.70 | +31: iteration 29500/ 39672 | consumed samples: 7552000 | consumed tokens: 15466496000 | elapsed time per iteration (s): 0.86 | learning rate: 4.819E-05 | global batch size: 256 | lm loss: 2.121578E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.310 | TFLOPs: 17.99 | +31: iteration 29510/ 39672 | consumed samples: 7554560 | consumed tokens: 15471738880 | elapsed time per iteration (s): 0.72 | learning rate: 4.813E-05 | global batch size: 256 | lm loss: 2.118266E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 353.713 | TFLOPs: 21.40 | +31: iteration 29520/ 39672 | consumed samples: 7557120 | consumed tokens: 15476981760 | elapsed time per iteration (s): 0.78 | learning rate: 4.808E-05 | global batch size: 256 | lm loss: 2.114811E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.165 | TFLOPs: 19.85 | +31: iteration 29530/ 39672 | consumed samples: 7559680 | consumed tokens: 15482224640 | elapsed time per iteration (s): 0.74 | learning rate: 4.803E-05 | global batch size: 256 | lm loss: 2.087670E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.679 | TFLOPs: 20.97 | +31: iteration 29540/ 39672 | consumed samples: 7562240 | consumed tokens: 15487467520 | elapsed time per iteration (s): 0.81 | learning rate: 4.798E-05 | global batch size: 256 | lm loss: 2.117913E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.605 | TFLOPs: 19.09 | +31: iteration 29550/ 39672 | consumed samples: 7564800 | consumed tokens: 15492710400 | elapsed time per iteration (s): 1.02 | learning rate: 4.793E-05 | global batch size: 256 | lm loss: 2.083045E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 251.106 | TFLOPs: 15.19 | +31: iteration 29560/ 39672 | consumed samples: 7567360 | consumed tokens: 15497953280 | elapsed time per iteration (s): 0.88 | learning rate: 4.787E-05 | global batch size: 256 | lm loss: 2.094654E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 291.026 | TFLOPs: 17.61 | +31: iteration 29570/ 39672 | consumed samples: 7569920 | consumed tokens: 15503196160 | elapsed time per iteration (s): 0.82 | learning rate: 4.782E-05 | global batch size: 256 | lm loss: 2.092975E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.035 | TFLOPs: 18.82 | +31: iteration 29580/ 39672 | consumed samples: 7572480 | consumed tokens: 15508439040 | elapsed time per iteration (s): 0.76 | learning rate: 4.777E-05 | global batch size: 256 | lm loss: 2.114539E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.753 | TFLOPs: 20.43 | +31: iteration 29590/ 39672 | consumed samples: 7575040 | consumed tokens: 15513681920 | elapsed time per iteration (s): 0.82 | learning rate: 4.772E-05 | global batch size: 256 | lm loss: 2.087963E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.310 | TFLOPs: 18.95 | +31: iteration 29600/ 39672 | consumed samples: 7577600 | consumed tokens: 15518924800 | elapsed time per iteration (s): 0.73 | learning rate: 4.767E-05 | global batch size: 256 | lm loss: 2.129697E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.381 | TFLOPs: 21.26 | +31: iteration 29610/ 39672 | consumed samples: 7580160 | consumed tokens: 15524167680 | elapsed time per iteration (s): 0.76 | learning rate: 4.761E-05 | global batch size: 256 | lm loss: 2.084550E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.129 | TFLOPs: 20.27 | +31: iteration 29620/ 39672 | consumed samples: 7582720 | consumed tokens: 15529410560 | elapsed time per iteration (s): 0.82 | learning rate: 4.756E-05 | global batch size: 256 | lm loss: 2.106992E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.180 | TFLOPs: 18.89 | +31: iteration 29630/ 39672 | consumed samples: 7585280 | consumed tokens: 15534653440 | elapsed time per iteration (s): 0.79 | learning rate: 4.751E-05 | global batch size: 256 | lm loss: 2.082766E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.982 | TFLOPs: 19.72 | +31: iteration 29640/ 39672 | consumed samples: 7587840 | consumed tokens: 15539896320 | elapsed time per iteration (s): 0.77 | learning rate: 4.746E-05 | global batch size: 256 | lm loss: 2.103913E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.796 | TFLOPs: 20.19 | +31: iteration 29650/ 39672 | consumed samples: 7590400 | consumed tokens: 15545139200 | elapsed time per iteration (s): 0.76 | learning rate: 4.741E-05 | global batch size: 256 | lm loss: 2.088056E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.767 | TFLOPs: 20.43 | +31: iteration 29660/ 39672 | consumed samples: 7592960 | consumed tokens: 15550382080 | elapsed time per iteration (s): 0.88 | learning rate: 4.735E-05 | global batch size: 256 | lm loss: 2.102258E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 289.599 | TFLOPs: 17.52 | +31: iteration 29670/ 39672 | consumed samples: 7595520 | consumed tokens: 15555624960 | elapsed time per iteration (s): 0.73 | learning rate: 4.730E-05 | global batch size: 256 | lm loss: 2.102128E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.040 | TFLOPs: 21.30 | +31: iteration 29680/ 39672 | consumed samples: 7598080 | consumed tokens: 15560867840 | elapsed time per iteration (s): 0.79 | learning rate: 4.725E-05 | global batch size: 256 | lm loss: 2.119874E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.412 | TFLOPs: 19.69 | +31: iteration 29690/ 39672 | consumed samples: 7600640 | consumed tokens: 15566110720 | elapsed time per iteration (s): 0.80 | learning rate: 4.720E-05 | global batch size: 256 | lm loss: 2.072133E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.613 | TFLOPs: 19.40 | +31: iteration 29700/ 39672 | consumed samples: 7603200 | consumed tokens: 15571353600 | elapsed time per iteration (s): 0.86 | learning rate: 4.715E-05 | global batch size: 256 | lm loss: 2.093589E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.306 | TFLOPs: 18.05 | +31: iteration 29710/ 39672 | consumed samples: 7605760 | consumed tokens: 15576596480 | elapsed time per iteration (s): 0.80 | learning rate: 4.710E-05 | global batch size: 256 | lm loss: 2.096471E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.417 | TFLOPs: 19.32 | +31: iteration 29720/ 39672 | consumed samples: 7608320 | consumed tokens: 15581839360 | elapsed time per iteration (s): 0.84 | learning rate: 4.705E-05 | global batch size: 256 | lm loss: 2.098617E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.277 | TFLOPs: 18.35 | +31: iteration 29730/ 39672 | consumed samples: 7610880 | consumed tokens: 15587082240 | elapsed time per iteration (s): 0.82 | learning rate: 4.699E-05 | global batch size: 256 | lm loss: 2.118717E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.334 | TFLOPs: 18.90 | +31: iteration 29740/ 39672 | consumed samples: 7613440 | consumed tokens: 15592325120 | elapsed time per iteration (s): 0.85 | learning rate: 4.694E-05 | global batch size: 256 | lm loss: 2.107467E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.048 | TFLOPs: 18.15 | +31: iteration 29750/ 39672 | consumed samples: 7616000 | consumed tokens: 15597568000 | elapsed time per iteration (s): 0.83 | learning rate: 4.689E-05 | global batch size: 256 | lm loss: 2.097392E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.646 | TFLOPs: 18.73 | +31: iteration 29760/ 39672 | consumed samples: 7618560 | consumed tokens: 15602810880 | elapsed time per iteration (s): 0.85 | learning rate: 4.684E-05 | global batch size: 256 | lm loss: 2.084469E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.688 | TFLOPs: 18.31 | +31: iteration 29770/ 39672 | consumed samples: 7621120 | consumed tokens: 15608053760 | elapsed time per iteration (s): 0.83 | learning rate: 4.679E-05 | global batch size: 256 | lm loss: 2.102679E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.632 | TFLOPs: 18.61 | +31: iteration 29780/ 39672 | consumed samples: 7623680 | consumed tokens: 15613296640 | elapsed time per iteration (s): 0.85 | learning rate: 4.674E-05 | global batch size: 256 | lm loss: 2.057927E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.545 | TFLOPs: 18.24 | +31: iteration 29790/ 39672 | consumed samples: 7626240 | consumed tokens: 15618539520 | elapsed time per iteration (s): 0.74 | learning rate: 4.669E-05 | global batch size: 256 | lm loss: 2.105676E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.780 | TFLOPs: 21.04 | +31: iteration 29800/ 39672 | consumed samples: 7628800 | consumed tokens: 15623782400 | elapsed time per iteration (s): 0.77 | learning rate: 4.663E-05 | global batch size: 256 | lm loss: 2.124826E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.818 | TFLOPs: 20.13 | +31: iteration 29810/ 39672 | consumed samples: 7631360 | consumed tokens: 15629025280 | elapsed time per iteration (s): 0.73 | learning rate: 4.658E-05 | global batch size: 256 | lm loss: 2.085567E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.555 | TFLOPs: 21.15 | +31: iteration 29820/ 39672 | consumed samples: 7633920 | consumed tokens: 15634268160 | elapsed time per iteration (s): 0.76 | learning rate: 4.653E-05 | global batch size: 256 | lm loss: 2.086815E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.729 | TFLOPs: 20.25 | +31: iteration 29830/ 39672 | consumed samples: 7636480 | consumed tokens: 15639511040 | elapsed time per iteration (s): 0.71 | learning rate: 4.648E-05 | global batch size: 256 | lm loss: 2.113361E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.558 | TFLOPs: 21.75 | +31: iteration 29840/ 39672 | consumed samples: 7639040 | consumed tokens: 15644753920 | elapsed time per iteration (s): 0.72 | learning rate: 4.643E-05 | global batch size: 256 | lm loss: 2.077129E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.793 | TFLOPs: 21.46 | +31: iteration 29850/ 39672 | consumed samples: 7641600 | consumed tokens: 15649996800 | elapsed time per iteration (s): 0.74 | learning rate: 4.638E-05 | global batch size: 256 | lm loss: 2.071545E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.810 | TFLOPs: 20.80 | +31: iteration 29860/ 39672 | consumed samples: 7644160 | consumed tokens: 15655239680 | elapsed time per iteration (s): 0.76 | learning rate: 4.633E-05 | global batch size: 256 | lm loss: 2.088437E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.214 | TFLOPs: 20.46 | +31: iteration 29870/ 39672 | consumed samples: 7646720 | consumed tokens: 15660482560 | elapsed time per iteration (s): 0.79 | learning rate: 4.628E-05 | global batch size: 256 | lm loss: 2.080113E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.759 | TFLOPs: 19.53 | +31: iteration 29880/ 39672 | consumed samples: 7649280 | consumed tokens: 15665725440 | elapsed time per iteration (s): 0.75 | learning rate: 4.623E-05 | global batch size: 256 | lm loss: 2.098191E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.374 | TFLOPs: 20.65 | +31: iteration 29890/ 39672 | consumed samples: 7651840 | consumed tokens: 15670968320 | elapsed time per iteration (s): 0.87 | learning rate: 4.618E-05 | global batch size: 256 | lm loss: 2.098752E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 292.775 | TFLOPs: 17.71 | +31: iteration 29900/ 39672 | consumed samples: 7654400 | consumed tokens: 15676211200 | elapsed time per iteration (s): 0.82 | learning rate: 4.613E-05 | global batch size: 256 | lm loss: 2.117177E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.902 | TFLOPs: 18.99 | +31: iteration 29910/ 39672 | consumed samples: 7656960 | consumed tokens: 15681454080 | elapsed time per iteration (s): 0.80 | learning rate: 4.608E-05 | global batch size: 256 | lm loss: 2.093278E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.448 | TFLOPs: 19.33 | +31: iteration 29920/ 39672 | consumed samples: 7659520 | consumed tokens: 15686696960 | elapsed time per iteration (s): 0.86 | learning rate: 4.602E-05 | global batch size: 256 | lm loss: 2.101367E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.099 | TFLOPs: 18.09 | +31: iteration 29930/ 39672 | consumed samples: 7662080 | consumed tokens: 15691939840 | elapsed time per iteration (s): 0.82 | learning rate: 4.597E-05 | global batch size: 256 | lm loss: 2.084374E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.663 | TFLOPs: 18.85 | +31: iteration 29940/ 39672 | consumed samples: 7664640 | consumed tokens: 15697182720 | elapsed time per iteration (s): 0.83 | learning rate: 4.592E-05 | global batch size: 256 | lm loss: 2.079716E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.798 | TFLOPs: 18.68 | +31: iteration 29950/ 39672 | consumed samples: 7667200 | consumed tokens: 15702425600 | elapsed time per iteration (s): 0.82 | learning rate: 4.587E-05 | global batch size: 256 | lm loss: 2.103959E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.813 | TFLOPs: 18.86 | +31: iteration 29960/ 39672 | consumed samples: 7669760 | consumed tokens: 15707668480 | elapsed time per iteration (s): 0.73 | learning rate: 4.582E-05 | global batch size: 256 | lm loss: 2.099030E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.426 | TFLOPs: 21.26 | +31: iteration 29970/ 39672 | consumed samples: 7672320 | consumed tokens: 15712911360 | elapsed time per iteration (s): 0.75 | learning rate: 4.577E-05 | global batch size: 256 | lm loss: 2.084025E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.119 | TFLOPs: 20.70 | +31: iteration 29980/ 39672 | consumed samples: 7674880 | consumed tokens: 15718154240 | elapsed time per iteration (s): 0.76 | learning rate: 4.572E-05 | global batch size: 256 | lm loss: 2.089975E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.813 | TFLOPs: 20.50 | +31: iteration 29990/ 39672 | consumed samples: 7677440 | consumed tokens: 15723397120 | elapsed time per iteration (s): 0.76 | learning rate: 4.567E-05 | global batch size: 256 | lm loss: 2.106498E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.391 | TFLOPs: 20.47 | + 0: [2022-11-30 15:50:26,401] [INFO] [logging.py:68:log_dist] [Rank 0] step=30000, skipped=0, lr=[4.562065401859714e-05, 4.562065401859714e-05, 4.562065401859714e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 30000/ 39672 | consumed samples: 7680000 | consumed tokens: 15728640000 | elapsed time per iteration (s): 0.74 | learning rate: 4.562E-05 | global batch size: 256 | lm loss: 2.112693E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.888 | TFLOPs: 20.80 | + 0: steps: 30000 loss: 2.0873 iter time (s): 0.791 samples/sec: 323.694 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 30000 | lm loss value: 2.141228E+00 | lm loss PPL: 8.509885E+00 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 30000 to checkpoints_1b121b + 0: [2022-11-30 15:50:26,700] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step30000 is begin to save! + 0: [2022-11-30 15:50:26,761] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_01-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_01-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,110] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_03-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_03-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,193] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_04-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_04-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,275] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_05-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,361] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_05-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,361] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_06-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_06-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,443] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_07-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_07-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,528] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_08-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_08-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,612] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_09-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_09-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,691] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_10-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_10-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,765] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_11-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_11-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,843] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_12-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_12-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,918] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_13-model_00-model_states.pt... + 0: [2022-11-30 15:50:27,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_13-model_00-model_states.pt. + 0: [2022-11-30 15:50:27,995] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_14-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_14-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,071] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_15-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_15-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,146] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_16-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_16-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,224] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_17-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_17-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,297] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_18-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_18-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,375] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_19-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_19-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_20-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_20-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_21-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_21-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,603] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_22-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_22-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,677] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_23-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_23-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,753] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_24-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_24-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,828] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_25-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_25-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,903] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_26-model_00-model_states.pt... + 0: [2022-11-30 15:50:28,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_26-model_00-model_states.pt. + 0: [2022-11-30 15:50:28,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_27-model_00-model_states.pt... + 0: [2022-11-30 15:50:29,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_27-model_00-model_states.pt. + 0: [2022-11-30 15:50:29,052] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_28-model_00-model_states.pt... + 0: [2022-11-30 15:50:29,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_28-model_00-model_states.pt. + 0: [2022-11-30 15:50:29,126] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/layer_30-model_00-model_states.pt... + 0: [2022-11-30 15:50:29,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/layer_30-model_00-model_states.pt. + 0: [2022-11-30 15:50:29,129] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_1b121b/global_step30000/mp_rank_00_model_states.pt + 0: [2022-11-30 15:50:29,130] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/mp_rank_00_model_states.pt... + 0: [2022-11-30 15:50:29,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/mp_rank_00_model_states.pt. + 0: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +31: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... + 0: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +21: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 0: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +19: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +12: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... + 8: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +23: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +21: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +29: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +24: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +13: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +30: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... + 6: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +27: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +31: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 7: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +20: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +17: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +22: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +16: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +15: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... + 2: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 4: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +14: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +18: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +28: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... + 0: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +19: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +12: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... + 8: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 3: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +23: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +21: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +29: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +24: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... + 5: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +13: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +30: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +10: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... + 6: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +27: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +31: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 7: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 9: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +20: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +17: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +22: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +26: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +16: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... + 1: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +15: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... + 2: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 4: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +14: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +18: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +28: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... + 0: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +19: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +12: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... + 8: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 3: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +23: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +21: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +29: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +24: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... + 5: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +13: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +30: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +10: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... + 6: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +27: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +25: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +31: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 9: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +20: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +22: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +26: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +16: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... + 1: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +15: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... + 2: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +18: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... + 0: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +19: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +12: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... + 8: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 3: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +23: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +21: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +29: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... + 5: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +30: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +10: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... + 6: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +27: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... + 9: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +11: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +20: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +16: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... + 1: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +15: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... + 0: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +10: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +27: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +11: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +16: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... + 1: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 1: [2022-11-30 15:50:29,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 3: [2022-11-30 15:50:29,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-30 15:50:29,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-30 15:50:29,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-30 15:50:29,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-30 15:50:29,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-30 15:50:29,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-30 15:50:29,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-30 15:50:29,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-30 15:50:29,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-30 15:50:29,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-30 15:50:29,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-30 15:50:29,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-30 15:50:29,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-30 15:50:29,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-30 15:50:29,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-30 15:50:29,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-30 15:50:29,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-30 15:50:29,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-30 15:50:29,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-30 15:50:29,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-30 15:50:29,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-30 15:50:29,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +15: [2022-11-30 15:50:29,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 3: [2022-11-30 15:50:29,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +15: [2022-11-30 15:50:29,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-30 15:50:29,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-30 15:50:29,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-30 15:50:29,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-30 15:50:29,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-30 15:50:29,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-30 15:50:29,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-30 15:50:29,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-30 15:50:29,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-30 15:50:29,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-30 15:50:29,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-30 15:50:29,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-30 15:50:29,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-30 15:50:29,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-30 15:50:29,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-30 15:50:29,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-30 15:50:29,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +29: [2022-11-30 15:50:29,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-30 15:50:29,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-30 15:50:29,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-30 15:50:29,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-30 15:50:29,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-30 15:50:29,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-30 15:50:29,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-30 15:50:29,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-30 15:50:29,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-30 15:50:29,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-30 15:50:29,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-30 15:50:29,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-30 15:50:29,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-30 15:50:29,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-30 15:50:29,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-30 15:50:29,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-30 15:50:29,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-30 15:50:29,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-30 15:50:29,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-30 15:50:29,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-30 15:50:29,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-30 15:50:29,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-30 15:50:29,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-30 15:50:29,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-30 15:50:29,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-30 15:50:29,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-30 15:50:29,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-30 15:50:29,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-30 15:50:29,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-30 15:50:29,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-30 15:50:29,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-30 15:50:29,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-30 15:50:29,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-30 15:50:29,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-30 15:50:29,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-30 15:50:29,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-30 15:50:29,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-30 15:50:29,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-30 15:50:29,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-30 15:50:29,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-30 15:50:29,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-30 15:50:29,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-30 15:50:29,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-30 15:50:29,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-30 15:50:29,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-30 15:50:29,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-30 15:50:29,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-30 15:50:29,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-30 15:50:29,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-30 15:50:29,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-30 15:50:29,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-30 15:50:29,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-30 15:50:29,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-30 15:50:29,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-30 15:50:29,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-30 15:50:29,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-30 15:50:29,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-30 15:50:29,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-30 15:50:29,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-30 15:50:29,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-30 15:50:29,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-30 15:50:29,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-30 15:50:29,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-30 15:50:29,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-30 15:50:29,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 0: [2022-11-30 15:50:29,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-30 15:50:29,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +16: [2022-11-30 15:50:29,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 0: [2022-11-30 15:50:29,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-30 15:50:29,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt + 0: [2022-11-30 15:50:29,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-30 15:50:29,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +16: [2022-11-30 15:50:29,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-30 15:50:29,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 0: [2022-11-30 15:50:29,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-30 15:50:29,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt + 0: [2022-11-30 15:50:29,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-30 15:50:29,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-30 15:50:29,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-30 15:50:29,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-30 15:50:29,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-30 15:50:29,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-30 15:50:29,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-30 15:50:29,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-30 15:50:29,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-30 15:50:29,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-30 15:50:29,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-30 15:50:29,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-30 15:50:29,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-30 15:50:29,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-30 15:50:29,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-30 15:50:29,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-30 15:50:29,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-30 15:50:29,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-30 15:50:29,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-30 15:50:29,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-30 15:50:29,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-30 15:50:29,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-30 15:50:29,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-30 15:50:29,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-30 15:50:29,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-30 15:50:29,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-30 15:50:29,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-30 15:50:29,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-30 15:50:29,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-30 15:50:29,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-30 15:50:29,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-30 15:50:29,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-30 15:50:29,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-30 15:50:29,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-30 15:50:29,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-30 15:50:29,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-30 15:50:29,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-30 15:50:29,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-30 15:50:29,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-30 15:50:29,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-30 15:50:29,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-30 15:50:29,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-30 15:50:29,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-30 15:50:29,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-30 15:50:29,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-30 15:50:29,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-30 15:50:29,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-30 15:50:29,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-30 15:50:29,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-30 15:50:29,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-30 15:50:29,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-30 15:50:29,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-30 15:50:29,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-30 15:50:29,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-30 15:50:29,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-30 15:50:29,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-30 15:50:29,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-30 15:50:29,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-30 15:50:29,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-30 15:50:29,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-30 15:50:29,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-30 15:50:29,330] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-30 15:50:29,330] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-30 15:50:29,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-30 15:50:29,330] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-30 15:50:29,330] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-30 15:50:29,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-30 15:50:29,330] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-30 15:50:29,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-30 15:50:29,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-30 15:50:29,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-30 15:50:29,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-30 15:50:29,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-30 15:50:29,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-30 15:50:29,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-30 15:50:29,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-30 15:50:29,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-30 15:50:29,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-30 15:50:29,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-30 15:50:29,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-30 15:50:29,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-30 15:50:29,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-30 15:50:29,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-30 15:50:29,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-30 15:50:29,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-30 15:50:29,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-30 15:50:29,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-30 15:50:29,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-30 15:50:29,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-30 15:50:29,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-30 15:50:29,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-30 15:50:29,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-30 15:50:29,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-30 15:50:29,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-30 15:50:29,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-30 15:50:29,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-30 15:50:29,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-30 15:50:29,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-30 15:50:29,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-30 15:50:29,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-30 15:50:29,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-30 15:50:29,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-30 15:50:29,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-30 15:50:29,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-30 15:50:29,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-30 15:50:29,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-30 15:50:29,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-30 15:50:29,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-30 15:50:29,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-30 15:50:29,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-30 15:50:29,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-30 15:50:29,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-30 15:50:29,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-30 15:50:29,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-30 15:50:29,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +24: [2022-11-30 15:50:29,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-30 15:50:29,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-30 15:50:29,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-30 15:50:29,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-30 15:50:29,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-30 15:50:29,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-30 15:50:29,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-30 15:50:29,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-30 15:50:29,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-30 15:50:29,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-30 15:50:29,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-30 15:50:29,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-30 15:50:29,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-30 15:50:29,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-30 15:50:29,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-30 15:50:29,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-30 15:50:29,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-30 15:50:29,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-30 15:50:29,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-30 15:50:29,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-30 15:50:29,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-30 15:50:29,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-30 15:50:29,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-30 15:50:29,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +23: [2022-11-30 15:50:29,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-30 15:50:29,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-30 15:50:29,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-30 15:50:29,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-30 15:50:29,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-30 15:50:29,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-30 15:50:29,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-30 15:50:29,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-30 15:50:29,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-30 15:50:29,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-30 15:50:29,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-30 15:50:29,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-30 15:50:29,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-30 15:50:29,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-30 15:50:29,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-30 15:50:29,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-30 15:50:29,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-30 15:50:29,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-30 15:50:29,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-30 15:50:29,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-30 15:50:29,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-30 15:50:29,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-30 15:50:29,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-30 15:50:29,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-30 15:50:29,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-30 15:50:29,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-30 15:50:29,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-30 15:50:29,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-30 15:50:29,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-30 15:50:29,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-30 15:50:29,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-30 15:50:29,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-30 15:50:29,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-30 15:50:29,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +20: [2022-11-30 15:50:29,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-30 15:50:29,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-30 15:50:29,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-30 15:50:29,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-30 15:50:29,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +25: [2022-11-30 15:50:29,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-30 15:50:29,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-30 15:50:29,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-30 15:50:29,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 7: [2022-11-30 15:50:29,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-30 15:50:29,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +22: [2022-11-30 15:50:29,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-30 15:50:29,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-30 15:50:29,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-30 15:50:29,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 8: [2022-11-30 15:50:29,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-30 15:50:29,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-30 15:50:29,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-30 15:50:29,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt + 7: [2022-11-30 15:50:29,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 2: [2022-11-30 15:50:29,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-30 15:50:29,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 8: [2022-11-30 15:50:29,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-30 15:50:29,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 5: [2022-11-30 15:50:29,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-30 15:50:29,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +25: [2022-11-30 15:50:29,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt + 7: [2022-11-30 15:50:29,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 2: [2022-11-30 15:50:29,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 8: [2022-11-30 15:50:29,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-30 15:50:29,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-30 15:50:29,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-30 15:50:29,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-30 15:50:29,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +22: [2022-11-30 15:50:29,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-30 15:50:29,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt + 2: [2022-11-30 15:50:29,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-30 15:50:29,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-30 15:50:29,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-30 15:50:29,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-30 15:50:29,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-30 15:50:29,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-30 15:50:29,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt +22: [2022-11-30 15:50:29,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-30 15:50:29,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 2: [2022-11-30 15:50:29,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 8: [2022-11-30 15:50:29,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-30 15:50:29,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-30 15:50:29,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-30 15:50:29,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-30 15:50:29,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-30 15:50:29,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 9: [2022-11-30 15:50:29,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-30 15:50:29,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-30 15:50:29,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-30 15:50:29,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 8: [2022-11-30 15:50:29,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-30 15:50:29,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-30 15:50:29,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 9: [2022-11-30 15:50:29,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-30 15:50:29,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +22: [2022-11-30 15:50:29,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-30 15:50:29,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-30 15:50:29,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-30 15:50:29,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-30 15:50:29,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 7: [2022-11-30 15:50:29,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-30 15:50:29,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 2: [2022-11-30 15:50:29,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 7: [2022-11-30 15:50:29,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 2: [2022-11-30 15:50:29,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-30 15:50:29,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 7: [2022-11-30 15:50:29,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-30 15:50:29,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +22: [2022-11-30 15:50:29,354] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt + 9: [2022-11-30 15:50:29,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +22: [2022-11-30 15:50:29,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-30 15:50:29,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-30 15:50:29,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-30 15:50:29,357] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-30 15:50:29,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-30 15:50:29,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-30 15:50:29,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-30 15:50:29,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-30 15:50:29,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-30 15:50:29,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-30 15:50:29,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-30 15:50:29,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-30 15:50:29,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-30 15:50:29,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-30 15:50:29,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-30 15:50:29,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-30 15:50:29,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-30 15:50:29,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-30 15:50:29,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-30 15:50:29,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-30 15:50:29,365] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-30 15:50:29,365] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-30 15:50:29,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-30 15:50:29,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-30 15:50:29,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-30 15:50:29,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-30 15:50:29,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-30 15:50:29,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-30 15:50:29,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-30 15:50:29,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-30 15:50:29,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-30 15:50:29,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-30 15:50:29,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-30 15:50:29,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-30 15:50:29,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-30 15:50:29,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-30 15:50:29,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-30 15:50:29,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-30 15:50:29,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-30 15:50:29,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-30 15:50:29,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-30 15:50:29,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-30 15:50:29,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-30 15:50:29,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-30 15:50:29,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-30 15:50:29,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-30 15:50:29,373] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-30 15:50:29,373] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-30 15:50:29,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-30 15:50:29,373] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-30 15:50:29,373] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-30 15:50:29,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-30 15:50:29,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-30 15:50:29,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-30 15:50:29,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. + 8: [2022-11-30 15:50:29,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +27: [2022-11-30 15:50:29,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-30 15:50:29,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-30 15:50:29,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-30 15:50:29,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-30 15:50:29,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-30 15:50:29,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-30 15:50:29,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-30 15:50:29,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-30 15:50:29,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-30 15:50:29,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-30 15:50:29,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-30 15:50:29,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-30 15:50:29,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-30 15:50:29,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,379] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-30 15:50:29,379] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-30 15:50:29,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-30 15:50:29,379] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-30 15:50:29,379] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-30 15:50:29,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-30 15:50:29,379] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-30 15:50:29,379] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-30 15:50:29,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-30 15:50:29,380] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-30 15:50:29,380] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-30 15:50:29,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-30 15:50:29,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-30 15:50:29,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-30 15:50:29,384] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-30 15:50:29,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-30 15:50:29,386] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,386] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-30 15:50:29,386] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-30 15:50:29,386] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-30 15:50:29,386] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-30 15:50:29,386] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-30 15:50:29,386] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-30 15:50:29,386] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-30 15:50:29,386] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-30 15:50:29,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-30 15:50:29,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-30 15:50:29,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-30 15:50:29,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +24: [2022-11-30 15:50:29,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. + 1: [2022-11-30 15:50:29,389] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-30 15:50:29,389] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-30 15:50:29,389] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-30 15:50:29,389] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-30 15:50:29,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-30 15:50:29,390] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-30 15:50:29,390] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-30 15:50:29,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-30 15:50:29,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-30 15:50:29,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-30 15:50:29,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-30 15:50:29,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-30 15:50:29,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-30 15:50:29,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 6: [2022-11-30 15:50:29,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 4: [2022-11-30 15:50:29,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 6: [2022-11-30 15:50:29,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 4: [2022-11-30 15:50:29,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-30 15:50:29,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-30 15:50:29,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +28: [2022-11-30 15:50:29,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +22: [2022-11-30 15:50:29,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +28: [2022-11-30 15:50:29,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +22: [2022-11-30 15:50:29,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-30 15:50:29,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-30 15:50:29,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-30 15:50:29,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-30 15:50:29,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-30 15:50:29,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-30 15:50:29,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-30 15:50:29,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-30 15:50:29,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-30 15:50:29,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-30 15:50:29,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-30 15:50:29,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-30 15:50:29,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-30 15:50:29,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-30 15:50:29,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-30 15:50:29,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +31: [2022-11-30 15:50:29,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +19: [2022-11-30 15:50:29,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-30 15:50:29,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-30 15:50:29,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-30 15:50:29,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +10: [2022-11-30 15:50:29,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. + 5: [2022-11-30 15:50:29,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +10: [2022-11-30 15:50:29,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt + 5: [2022-11-30 15:50:29,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-30 15:50:29,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-30 15:50:29,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-30 15:50:29,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-30 15:50:29,404] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-30 15:50:29,404] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-30 15:50:29,404] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-30 15:50:29,404] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-30 15:50:29,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-30 15:50:29,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-30 15:50:29,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-30 15:50:29,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-30 15:50:29,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-30 15:50:29,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-30 15:50:29,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-30 15:50:29,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-30 15:50:29,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-30 15:50:29,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-30 15:50:29,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-30 15:50:29,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-30 15:50:29,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-30 15:50:29,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-30 15:50:29,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-30 15:50:29,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-30 15:50:29,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-30 15:50:29,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-30 15:50:29,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-30 15:50:29,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-30 15:50:29,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-30 15:50:29,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-30 15:50:29,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-30 15:50:29,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-30 15:50:29,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. + 7: [2022-11-30 15:50:29,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-30 15:50:29,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-30 15:50:29,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-30 15:50:29,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-30 15:50:29,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-30 15:50:29,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-30 15:50:29,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-30 15:50:29,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-30 15:50:29,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-30 15:50:29,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-30 15:50:29,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-30 15:50:29,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-30 15:50:29,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-30 15:50:29,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-30 15:50:29,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-30 15:50:29,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-30 15:50:29,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-30 15:50:29,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-30 15:50:29,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-30 15:50:29,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-30 15:50:29,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-30 15:50:29,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-30 15:50:29,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-30 15:50:29,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-30 15:50:29,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-30 15:50:29,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-30 15:50:29,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-30 15:50:29,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-30 15:50:29,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-30 15:50:29,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. + 2: [2022-11-30 15:50:29,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +20: [2022-11-30 15:50:29,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-30 15:50:29,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-30 15:50:29,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-30 15:50:29,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-30 15:50:29,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-30 15:50:29,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-30 15:50:29,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-30 15:50:29,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-30 15:50:29,438] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-30 15:50:29,438] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-30 15:50:29,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +21: [2022-11-30 15:50:29,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +14: [2022-11-30 15:50:29,438] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-30 15:50:29,438] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-30 15:50:29,438] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-30 15:50:29,438] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-30 15:50:29,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-30 15:50:29,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-30 15:50:29,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-30 15:50:29,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-30 15:50:29,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-30 15:50:29,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-30 15:50:29,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt + 8: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-30 15:50:29,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt +16: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt + 8: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +16: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-30 15:50:29,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-30 15:50:29,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +25: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +12: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-30 15:50:29,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-30 15:50:29,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-30 15:50:29,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-30 15:50:29,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-30 15:50:29,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-30 15:50:29,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-30 15:50:29,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-30 15:50:29,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-30 15:50:29,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-30 15:50:29,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-30 15:50:29,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-30 15:50:29,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-30 15:50:29,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +24: [2022-11-30 15:50:29,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +17: [2022-11-30 15:50:29,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-30 15:50:29,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-30 15:50:29,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-30 15:50:29,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-30 15:50:29,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-30 15:50:29,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-30 15:50:29,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-30 15:50:29,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-30 15:50:29,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-30 15:50:29,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-30 15:50:29,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-30 15:50:29,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-30 15:50:29,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-30 15:50:29,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-30 15:50:29,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-30 15:50:29,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-30 15:50:29,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +23: [2022-11-30 15:50:29,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. + 7: [2022-11-30 15:50:29,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-30 15:50:29,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-30 15:50:29,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-30 15:50:29,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-30 15:50:29,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-30 15:50:29,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: successfully saved checkpoint at iteration 30000 to checkpoints_1b121b +31: time (ms) | save-checkpoint: 2795.91 +31: iteration 30010/ 39672 | consumed samples: 7682560 | consumed tokens: 15733882880 | elapsed time per iteration (s): 1.05 | learning rate: 4.557E-05 | global batch size: 256 | lm loss: 2.089892E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 243.471 | TFLOPs: 14.73 | +31: iteration 30020/ 39672 | consumed samples: 7685120 | consumed tokens: 15739125760 | elapsed time per iteration (s): 0.74 | learning rate: 4.552E-05 | global batch size: 256 | lm loss: 2.111102E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.831 | TFLOPs: 20.80 | +31: iteration 30030/ 39672 | consumed samples: 7687680 | consumed tokens: 15744368640 | elapsed time per iteration (s): 0.76 | learning rate: 4.547E-05 | global batch size: 256 | lm loss: 2.110782E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.481 | TFLOPs: 20.42 | +31: iteration 30040/ 39672 | consumed samples: 7690240 | consumed tokens: 15749611520 | elapsed time per iteration (s): 0.79 | learning rate: 4.542E-05 | global batch size: 256 | lm loss: 2.087111E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.257 | TFLOPs: 19.62 | +31: iteration 30050/ 39672 | consumed samples: 7692800 | consumed tokens: 15754854400 | elapsed time per iteration (s): 0.77 | learning rate: 4.537E-05 | global batch size: 256 | lm loss: 2.106720E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.905 | TFLOPs: 20.08 | +31: iteration 30060/ 39672 | consumed samples: 7695360 | consumed tokens: 15760097280 | elapsed time per iteration (s): 0.78 | learning rate: 4.532E-05 | global batch size: 256 | lm loss: 2.111292E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.645 | TFLOPs: 19.82 | +31: iteration 30070/ 39672 | consumed samples: 7697920 | consumed tokens: 15765340160 | elapsed time per iteration (s): 0.78 | learning rate: 4.527E-05 | global batch size: 256 | lm loss: 2.103114E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.654 | TFLOPs: 19.82 | +31: iteration 30080/ 39672 | consumed samples: 7700480 | consumed tokens: 15770583040 | elapsed time per iteration (s): 0.76 | learning rate: 4.522E-05 | global batch size: 256 | lm loss: 2.113797E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.657 | TFLOPs: 20.37 | +31: iteration 30090/ 39672 | consumed samples: 7703040 | consumed tokens: 15775825920 | elapsed time per iteration (s): 0.81 | learning rate: 4.517E-05 | global batch size: 256 | lm loss: 2.088910E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.668 | TFLOPs: 19.04 | +31: iteration 30100/ 39672 | consumed samples: 7705600 | consumed tokens: 15781068800 | elapsed time per iteration (s): 0.77 | learning rate: 4.512E-05 | global batch size: 256 | lm loss: 2.082359E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.469 | TFLOPs: 20.11 | +31: iteration 30110/ 39672 | consumed samples: 7708160 | consumed tokens: 15786311680 | elapsed time per iteration (s): 0.86 | learning rate: 4.507E-05 | global batch size: 256 | lm loss: 2.111588E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.236 | TFLOPs: 17.92 | +31: iteration 30120/ 39672 | consumed samples: 7710720 | consumed tokens: 15791554560 | elapsed time per iteration (s): 0.76 | learning rate: 4.502E-05 | global batch size: 256 | lm loss: 2.086888E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.997 | TFLOPs: 20.45 | +31: iteration 30130/ 39672 | consumed samples: 7713280 | consumed tokens: 15796797440 | elapsed time per iteration (s): 0.76 | learning rate: 4.497E-05 | global batch size: 256 | lm loss: 2.100061E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.317 | TFLOPs: 20.29 | +31: iteration 30140/ 39672 | consumed samples: 7715840 | consumed tokens: 15802040320 | elapsed time per iteration (s): 0.77 | learning rate: 4.492E-05 | global batch size: 256 | lm loss: 2.102071E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.016 | TFLOPs: 20.21 | +31: iteration 30150/ 39672 | consumed samples: 7718400 | consumed tokens: 15807283200 | elapsed time per iteration (s): 0.78 | learning rate: 4.487E-05 | global batch size: 256 | lm loss: 2.101686E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.069 | TFLOPs: 19.91 | +31: iteration 30160/ 39672 | consumed samples: 7720960 | consumed tokens: 15812526080 | elapsed time per iteration (s): 0.76 | learning rate: 4.482E-05 | global batch size: 256 | lm loss: 2.107131E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.186 | TFLOPs: 20.40 | +31: iteration 30170/ 39672 | consumed samples: 7723520 | consumed tokens: 15817768960 | elapsed time per iteration (s): 0.78 | learning rate: 4.477E-05 | global batch size: 256 | lm loss: 2.093217E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.314 | TFLOPs: 19.92 | +31: iteration 30180/ 39672 | consumed samples: 7726080 | consumed tokens: 15823011840 | elapsed time per iteration (s): 0.80 | learning rate: 4.472E-05 | global batch size: 256 | lm loss: 2.101865E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.766 | TFLOPs: 19.28 | +31: iteration 30190/ 39672 | consumed samples: 7728640 | consumed tokens: 15828254720 | elapsed time per iteration (s): 0.76 | learning rate: 4.467E-05 | global batch size: 256 | lm loss: 2.087096E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.212 | TFLOPs: 20.46 | +31: iteration 30200/ 39672 | consumed samples: 7731200 | consumed tokens: 15833497600 | elapsed time per iteration (s): 0.76 | learning rate: 4.462E-05 | global batch size: 256 | lm loss: 2.104541E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.352 | TFLOPs: 20.35 | +31: iteration 30210/ 39672 | consumed samples: 7733760 | consumed tokens: 15838740480 | elapsed time per iteration (s): 0.82 | learning rate: 4.457E-05 | global batch size: 256 | lm loss: 2.073411E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.960 | TFLOPs: 18.81 | +31: iteration 30220/ 39672 | consumed samples: 7736320 | consumed tokens: 15843983360 | elapsed time per iteration (s): 0.72 | learning rate: 4.452E-05 | global batch size: 256 | lm loss: 2.102857E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.040 | TFLOPs: 21.54 | +31: iteration 30230/ 39672 | consumed samples: 7738880 | consumed tokens: 15849226240 | elapsed time per iteration (s): 0.83 | learning rate: 4.447E-05 | global batch size: 256 | lm loss: 2.095644E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.281 | TFLOPs: 18.59 | +31: iteration 30240/ 39672 | consumed samples: 7741440 | consumed tokens: 15854469120 | elapsed time per iteration (s): 0.74 | learning rate: 4.443E-05 | global batch size: 256 | lm loss: 2.069769E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.688 | TFLOPs: 20.79 | +31: iteration 30250/ 39672 | consumed samples: 7744000 | consumed tokens: 15859712000 | elapsed time per iteration (s): 0.79 | learning rate: 4.438E-05 | global batch size: 256 | lm loss: 2.125106E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.623 | TFLOPs: 19.52 | +31: iteration 30260/ 39672 | consumed samples: 7746560 | consumed tokens: 15864954880 | elapsed time per iteration (s): 0.78 | learning rate: 4.433E-05 | global batch size: 256 | lm loss: 2.117984E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.036 | TFLOPs: 19.85 | +31: iteration 30270/ 39672 | consumed samples: 7749120 | consumed tokens: 15870197760 | elapsed time per iteration (s): 0.80 | learning rate: 4.428E-05 | global batch size: 256 | lm loss: 2.099689E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.054 | TFLOPs: 19.30 | +31: iteration 30280/ 39672 | consumed samples: 7751680 | consumed tokens: 15875440640 | elapsed time per iteration (s): 0.77 | learning rate: 4.423E-05 | global batch size: 256 | lm loss: 2.117478E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.585 | TFLOPs: 20.06 | +31: iteration 30290/ 39672 | consumed samples: 7754240 | consumed tokens: 15880683520 | elapsed time per iteration (s): 0.81 | learning rate: 4.418E-05 | global batch size: 256 | lm loss: 2.119968E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.214 | TFLOPs: 19.13 | +31: iteration 30300/ 39672 | consumed samples: 7756800 | consumed tokens: 15885926400 | elapsed time per iteration (s): 0.77 | learning rate: 4.413E-05 | global batch size: 256 | lm loss: 2.075369E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.513 | TFLOPs: 20.24 | +31: iteration 30310/ 39672 | consumed samples: 7759360 | consumed tokens: 15891169280 | elapsed time per iteration (s): 0.78 | learning rate: 4.408E-05 | global batch size: 256 | lm loss: 2.076507E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.047 | TFLOPs: 19.97 | +31: iteration 30320/ 39672 | consumed samples: 7761920 | consumed tokens: 15896412160 | elapsed time per iteration (s): 0.76 | learning rate: 4.403E-05 | global batch size: 256 | lm loss: 2.115520E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.042 | TFLOPs: 20.39 | +31: iteration 30330/ 39672 | consumed samples: 7764480 | consumed tokens: 15901655040 | elapsed time per iteration (s): 0.76 | learning rate: 4.398E-05 | global batch size: 256 | lm loss: 2.090562E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.191 | TFLOPs: 20.40 | +31: iteration 30340/ 39672 | consumed samples: 7767040 | consumed tokens: 15906897920 | elapsed time per iteration (s): 0.78 | learning rate: 4.393E-05 | global batch size: 256 | lm loss: 2.100954E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.612 | TFLOPs: 19.88 | +31: iteration 30350/ 39672 | consumed samples: 7769600 | consumed tokens: 15912140800 | elapsed time per iteration (s): 0.77 | learning rate: 4.389E-05 | global batch size: 256 | lm loss: 2.077358E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.304 | TFLOPs: 20.22 | +31: iteration 30360/ 39672 | consumed samples: 7772160 | consumed tokens: 15917383680 | elapsed time per iteration (s): 0.77 | learning rate: 4.384E-05 | global batch size: 256 | lm loss: 2.113911E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.397 | TFLOPs: 19.99 | +31: iteration 30370/ 39672 | consumed samples: 7774720 | consumed tokens: 15922626560 | elapsed time per iteration (s): 0.84 | learning rate: 4.379E-05 | global batch size: 256 | lm loss: 2.095513E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.335 | TFLOPs: 18.47 | +31: iteration 30380/ 39672 | consumed samples: 7777280 | consumed tokens: 15927869440 | elapsed time per iteration (s): 0.81 | learning rate: 4.374E-05 | global batch size: 256 | lm loss: 2.119015E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.792 | TFLOPs: 19.23 | +31: iteration 30390/ 39672 | consumed samples: 7779840 | consumed tokens: 15933112320 | elapsed time per iteration (s): 0.88 | learning rate: 4.369E-05 | global batch size: 256 | lm loss: 2.120528E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 289.890 | TFLOPs: 17.54 | +31: iteration 30400/ 39672 | consumed samples: 7782400 | consumed tokens: 15938355200 | elapsed time per iteration (s): 0.79 | learning rate: 4.364E-05 | global batch size: 256 | lm loss: 2.106701E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.401 | TFLOPs: 19.69 | +31: iteration 30410/ 39672 | consumed samples: 7784960 | consumed tokens: 15943598080 | elapsed time per iteration (s): 0.81 | learning rate: 4.359E-05 | global batch size: 256 | lm loss: 2.080729E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.092 | TFLOPs: 19.06 | +31: iteration 30420/ 39672 | consumed samples: 7787520 | consumed tokens: 15948840960 | elapsed time per iteration (s): 0.79 | learning rate: 4.354E-05 | global batch size: 256 | lm loss: 2.088042E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.816 | TFLOPs: 19.71 | +31: iteration 30430/ 39672 | consumed samples: 7790080 | consumed tokens: 15954083840 | elapsed time per iteration (s): 0.85 | learning rate: 4.350E-05 | global batch size: 256 | lm loss: 2.081849E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.780 | TFLOPs: 18.32 | +31: iteration 30440/ 39672 | consumed samples: 7792640 | consumed tokens: 15959326720 | elapsed time per iteration (s): 0.75 | learning rate: 4.345E-05 | global batch size: 256 | lm loss: 2.115344E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.052 | TFLOPs: 20.57 | +31: iteration 30450/ 39672 | consumed samples: 7795200 | consumed tokens: 15964569600 | elapsed time per iteration (s): 0.73 | learning rate: 4.340E-05 | global batch size: 256 | lm loss: 2.079188E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.179 | TFLOPs: 21.18 | +31: iteration 30460/ 39672 | consumed samples: 7797760 | consumed tokens: 15969812480 | elapsed time per iteration (s): 0.77 | learning rate: 4.335E-05 | global batch size: 256 | lm loss: 2.075248E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.787 | TFLOPs: 20.13 | +31: iteration 30470/ 39672 | consumed samples: 7800320 | consumed tokens: 15975055360 | elapsed time per iteration (s): 0.75 | learning rate: 4.330E-05 | global batch size: 256 | lm loss: 2.106277E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.814 | TFLOPs: 20.56 | +31: iteration 30480/ 39672 | consumed samples: 7802880 | consumed tokens: 15980298240 | elapsed time per iteration (s): 0.78 | learning rate: 4.325E-05 | global batch size: 256 | lm loss: 2.090088E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.401 | TFLOPs: 19.87 | +31: iteration 30490/ 39672 | consumed samples: 7805440 | consumed tokens: 15985541120 | elapsed time per iteration (s): 0.83 | learning rate: 4.321E-05 | global batch size: 256 | lm loss: 2.104889E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.934 | TFLOPs: 18.69 | +31: iteration 30500/ 39672 | consumed samples: 7808000 | consumed tokens: 15990784000 | elapsed time per iteration (s): 0.82 | learning rate: 4.316E-05 | global batch size: 256 | lm loss: 2.079616E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.237 | TFLOPs: 18.95 | +31: iteration 30510/ 39672 | consumed samples: 7810560 | consumed tokens: 15996026880 | elapsed time per iteration (s): 0.82 | learning rate: 4.311E-05 | global batch size: 256 | lm loss: 2.102290E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.013 | TFLOPs: 18.88 | +31: iteration 30520/ 39672 | consumed samples: 7813120 | consumed tokens: 16001269760 | elapsed time per iteration (s): 0.83 | learning rate: 4.306E-05 | global batch size: 256 | lm loss: 2.094026E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.366 | TFLOPs: 18.66 | +31: iteration 30530/ 39672 | consumed samples: 7815680 | consumed tokens: 16006512640 | elapsed time per iteration (s): 0.80 | learning rate: 4.301E-05 | global batch size: 256 | lm loss: 2.084678E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.203 | TFLOPs: 19.37 | +31: iteration 30540/ 39672 | consumed samples: 7818240 | consumed tokens: 16011755520 | elapsed time per iteration (s): 0.78 | learning rate: 4.297E-05 | global batch size: 256 | lm loss: 2.065515E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.226 | TFLOPs: 19.74 | +31: iteration 30550/ 39672 | consumed samples: 7820800 | consumed tokens: 16016998400 | elapsed time per iteration (s): 0.77 | learning rate: 4.292E-05 | global batch size: 256 | lm loss: 2.110946E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.671 | TFLOPs: 20.00 | +31: iteration 30560/ 39672 | consumed samples: 7823360 | consumed tokens: 16022241280 | elapsed time per iteration (s): 0.76 | learning rate: 4.287E-05 | global batch size: 256 | lm loss: 2.113157E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.733 | TFLOPs: 20.37 | +31: iteration 30570/ 39672 | consumed samples: 7825920 | consumed tokens: 16027484160 | elapsed time per iteration (s): 0.83 | learning rate: 4.282E-05 | global batch size: 256 | lm loss: 2.128873E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.860 | TFLOPs: 18.75 | +31: iteration 30580/ 39672 | consumed samples: 7828480 | consumed tokens: 16032727040 | elapsed time per iteration (s): 0.76 | learning rate: 4.277E-05 | global batch size: 256 | lm loss: 2.058997E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.662 | TFLOPs: 20.49 | +31: iteration 30590/ 39672 | consumed samples: 7831040 | consumed tokens: 16037969920 | elapsed time per iteration (s): 0.79 | learning rate: 4.273E-05 | global batch size: 256 | lm loss: 2.104573E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.906 | TFLOPs: 19.66 | +31: iteration 30600/ 39672 | consumed samples: 7833600 | consumed tokens: 16043212800 | elapsed time per iteration (s): 0.76 | learning rate: 4.268E-05 | global batch size: 256 | lm loss: 2.101774E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.826 | TFLOPs: 20.32 | +31: iteration 30610/ 39672 | consumed samples: 7836160 | consumed tokens: 16048455680 | elapsed time per iteration (s): 0.79 | learning rate: 4.263E-05 | global batch size: 256 | lm loss: 2.093000E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.666 | TFLOPs: 19.70 | +31: iteration 30620/ 39672 | consumed samples: 7838720 | consumed tokens: 16053698560 | elapsed time per iteration (s): 0.75 | learning rate: 4.258E-05 | global batch size: 256 | lm loss: 2.097272E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.096 | TFLOPs: 20.51 | +31: iteration 30630/ 39672 | consumed samples: 7841280 | consumed tokens: 16058941440 | elapsed time per iteration (s): 0.75 | learning rate: 4.253E-05 | global batch size: 256 | lm loss: 2.077630E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.555 | TFLOPs: 20.78 | +31: iteration 30640/ 39672 | consumed samples: 7843840 | consumed tokens: 16064184320 | elapsed time per iteration (s): 0.79 | learning rate: 4.249E-05 | global batch size: 256 | lm loss: 2.071363E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.000 | TFLOPs: 19.72 | +31: iteration 30650/ 39672 | consumed samples: 7846400 | consumed tokens: 16069427200 | elapsed time per iteration (s): 0.82 | learning rate: 4.244E-05 | global batch size: 256 | lm loss: 2.103267E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.547 | TFLOPs: 18.85 | +31: iteration 30660/ 39672 | consumed samples: 7848960 | consumed tokens: 16074670080 | elapsed time per iteration (s): 0.80 | learning rate: 4.239E-05 | global batch size: 256 | lm loss: 2.095079E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.010 | TFLOPs: 19.42 | +31: iteration 30670/ 39672 | consumed samples: 7851520 | consumed tokens: 16079912960 | elapsed time per iteration (s): 0.83 | learning rate: 4.234E-05 | global batch size: 256 | lm loss: 2.107101E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.377 | TFLOPs: 18.60 | +31: iteration 30680/ 39672 | consumed samples: 7854080 | consumed tokens: 16085155840 | elapsed time per iteration (s): 0.79 | learning rate: 4.230E-05 | global batch size: 256 | lm loss: 2.139352E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.080 | TFLOPs: 19.49 | +31: iteration 30690/ 39672 | consumed samples: 7856640 | consumed tokens: 16090398720 | elapsed time per iteration (s): 0.82 | learning rate: 4.225E-05 | global batch size: 256 | lm loss: 2.117075E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.953 | TFLOPs: 18.87 | +31: iteration 30700/ 39672 | consumed samples: 7859200 | consumed tokens: 16095641600 | elapsed time per iteration (s): 0.90 | learning rate: 4.220E-05 | global batch size: 256 | lm loss: 2.109189E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 283.110 | TFLOPs: 17.13 | +31: iteration 30710/ 39672 | consumed samples: 7861760 | consumed tokens: 16100884480 | elapsed time per iteration (s): 0.79 | learning rate: 4.215E-05 | global batch size: 256 | lm loss: 2.091575E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.398 | TFLOPs: 19.56 | +31: iteration 30720/ 39672 | consumed samples: 7864320 | consumed tokens: 16106127360 | elapsed time per iteration (s): 0.76 | learning rate: 4.211E-05 | global batch size: 256 | lm loss: 2.088839E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.768 | TFLOPs: 20.37 | +31: iteration 30730/ 39672 | consumed samples: 7866880 | consumed tokens: 16111370240 | elapsed time per iteration (s): 0.77 | learning rate: 4.206E-05 | global batch size: 256 | lm loss: 2.094596E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.015 | TFLOPs: 20.21 | +31: iteration 30740/ 39672 | consumed samples: 7869440 | consumed tokens: 16116613120 | elapsed time per iteration (s): 0.76 | learning rate: 4.201E-05 | global batch size: 256 | lm loss: 2.078172E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.414 | TFLOPs: 20.41 | +31: iteration 30750/ 39672 | consumed samples: 7872000 | consumed tokens: 16121856000 | elapsed time per iteration (s): 0.75 | learning rate: 4.197E-05 | global batch size: 256 | lm loss: 2.090613E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.094 | TFLOPs: 20.51 | +31: iteration 30760/ 39672 | consumed samples: 7874560 | consumed tokens: 16127098880 | elapsed time per iteration (s): 0.73 | learning rate: 4.192E-05 | global batch size: 256 | lm loss: 2.087551E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.764 | TFLOPs: 21.16 | +31: iteration 30770/ 39672 | consumed samples: 7877120 | consumed tokens: 16132341760 | elapsed time per iteration (s): 0.72 | learning rate: 4.187E-05 | global batch size: 256 | lm loss: 2.072303E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.110 | TFLOPs: 21.48 | +31: iteration 30780/ 39672 | consumed samples: 7879680 | consumed tokens: 16137584640 | elapsed time per iteration (s): 0.73 | learning rate: 4.182E-05 | global batch size: 256 | lm loss: 2.099569E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.061 | TFLOPs: 21.24 | +31: iteration 30790/ 39672 | consumed samples: 7882240 | consumed tokens: 16142827520 | elapsed time per iteration (s): 0.75 | learning rate: 4.178E-05 | global batch size: 256 | lm loss: 2.052592E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.401 | TFLOPs: 20.53 | +31: iteration 30800/ 39672 | consumed samples: 7884800 | consumed tokens: 16148070400 | elapsed time per iteration (s): 0.76 | learning rate: 4.173E-05 | global batch size: 256 | lm loss: 2.098578E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.308 | TFLOPs: 20.47 | +31: iteration 30810/ 39672 | consumed samples: 7887360 | consumed tokens: 16153313280 | elapsed time per iteration (s): 0.78 | learning rate: 4.168E-05 | global batch size: 256 | lm loss: 2.076440E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.365 | TFLOPs: 19.74 | +31: iteration 30820/ 39672 | consumed samples: 7889920 | consumed tokens: 16158556160 | elapsed time per iteration (s): 0.79 | learning rate: 4.164E-05 | global batch size: 256 | lm loss: 2.091005E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.452 | TFLOPs: 19.69 | +31: iteration 30830/ 39672 | consumed samples: 7892480 | consumed tokens: 16163799040 | elapsed time per iteration (s): 0.75 | learning rate: 4.159E-05 | global batch size: 256 | lm loss: 2.078155E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.583 | TFLOPs: 20.79 | +31: iteration 30840/ 39672 | consumed samples: 7895040 | consumed tokens: 16169041920 | elapsed time per iteration (s): 0.82 | learning rate: 4.154E-05 | global batch size: 256 | lm loss: 2.109670E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.985 | TFLOPs: 19.00 | +31: iteration 30850/ 39672 | consumed samples: 7897600 | consumed tokens: 16174284800 | elapsed time per iteration (s): 0.82 | learning rate: 4.150E-05 | global batch size: 256 | lm loss: 2.099072E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.434 | TFLOPs: 18.78 | +31: iteration 30860/ 39672 | consumed samples: 7900160 | consumed tokens: 16179527680 | elapsed time per iteration (s): 0.80 | learning rate: 4.145E-05 | global batch size: 256 | lm loss: 2.087041E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.649 | TFLOPs: 19.40 | +31: iteration 30870/ 39672 | consumed samples: 7902720 | consumed tokens: 16184770560 | elapsed time per iteration (s): 0.80 | learning rate: 4.140E-05 | global batch size: 256 | lm loss: 2.110650E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.617 | TFLOPs: 19.28 | +31: iteration 30880/ 39672 | consumed samples: 7905280 | consumed tokens: 16190013440 | elapsed time per iteration (s): 1.01 | learning rate: 4.136E-05 | global batch size: 256 | lm loss: 2.076561E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 252.466 | TFLOPs: 15.27 | +31: iteration 30890/ 39672 | consumed samples: 7907840 | consumed tokens: 16195256320 | elapsed time per iteration (s): 0.79 | learning rate: 4.131E-05 | global batch size: 256 | lm loss: 2.095183E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.284 | TFLOPs: 19.62 | +31: iteration 30900/ 39672 | consumed samples: 7910400 | consumed tokens: 16200499200 | elapsed time per iteration (s): 0.79 | learning rate: 4.126E-05 | global batch size: 256 | lm loss: 2.077278E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.903 | TFLOPs: 19.60 | +31: iteration 30910/ 39672 | consumed samples: 7912960 | consumed tokens: 16205742080 | elapsed time per iteration (s): 0.87 | learning rate: 4.122E-05 | global batch size: 256 | lm loss: 2.078280E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 293.132 | TFLOPs: 17.73 | +31: iteration 30920/ 39672 | consumed samples: 7915520 | consumed tokens: 16210984960 | elapsed time per iteration (s): 0.84 | learning rate: 4.117E-05 | global batch size: 256 | lm loss: 2.102837E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.366 | TFLOPs: 18.47 | +31: iteration 30930/ 39672 | consumed samples: 7918080 | consumed tokens: 16216227840 | elapsed time per iteration (s): 0.82 | learning rate: 4.112E-05 | global batch size: 256 | lm loss: 2.087238E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.756 | TFLOPs: 18.80 | +31: iteration 30940/ 39672 | consumed samples: 7920640 | consumed tokens: 16221470720 | elapsed time per iteration (s): 0.80 | learning rate: 4.108E-05 | global batch size: 256 | lm loss: 2.099304E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.695 | TFLOPs: 19.40 | +31: iteration 30950/ 39672 | consumed samples: 7923200 | consumed tokens: 16226713600 | elapsed time per iteration (s): 0.82 | learning rate: 4.103E-05 | global batch size: 256 | lm loss: 2.075067E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.602 | TFLOPs: 18.97 | +31: iteration 30960/ 39672 | consumed samples: 7925760 | consumed tokens: 16231956480 | elapsed time per iteration (s): 0.80 | learning rate: 4.099E-05 | global batch size: 256 | lm loss: 2.108606E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.847 | TFLOPs: 19.41 | +31: iteration 30970/ 39672 | consumed samples: 7928320 | consumed tokens: 16237199360 | elapsed time per iteration (s): 0.74 | learning rate: 4.094E-05 | global batch size: 256 | lm loss: 2.101141E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.693 | TFLOPs: 20.85 | +31: iteration 30980/ 39672 | consumed samples: 7930880 | consumed tokens: 16242442240 | elapsed time per iteration (s): 0.81 | learning rate: 4.089E-05 | global batch size: 256 | lm loss: 2.057968E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.977 | TFLOPs: 19.12 | +31: iteration 30990/ 39672 | consumed samples: 7933440 | consumed tokens: 16247685120 | elapsed time per iteration (s): 0.73 | learning rate: 4.085E-05 | global batch size: 256 | lm loss: 2.089530E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.568 | TFLOPs: 21.15 | +31: iteration 31000/ 39672 | consumed samples: 7936000 | consumed tokens: 16252928000 | elapsed time per iteration (s): 0.78 | learning rate: 4.080E-05 | global batch size: 256 | lm loss: 2.097200E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.170 | TFLOPs: 19.85 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 31000 | lm loss value: 2.004091E+00 | lm loss PPL: 7.419343E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 31010/ 39672 | consumed samples: 7938560 | consumed tokens: 16258170880 | elapsed time per iteration (s): 0.75 | learning rate: 4.076E-05 | global batch size: 256 | lm loss: 2.104731E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.144 | TFLOPs: 20.58 | +31: iteration 31020/ 39672 | consumed samples: 7941120 | consumed tokens: 16263413760 | elapsed time per iteration (s): 0.78 | learning rate: 4.071E-05 | global batch size: 256 | lm loss: 2.142703E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.489 | TFLOPs: 19.87 | +31: iteration 31030/ 39672 | consumed samples: 7943680 | consumed tokens: 16268656640 | elapsed time per iteration (s): 0.75 | learning rate: 4.066E-05 | global batch size: 256 | lm loss: 2.088820E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.647 | TFLOPs: 20.61 | +31: iteration 31040/ 39672 | consumed samples: 7946240 | consumed tokens: 16273899520 | elapsed time per iteration (s): 0.75 | learning rate: 4.062E-05 | global batch size: 256 | lm loss: 2.152749E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.306 | TFLOPs: 20.65 | +31: iteration 31050/ 39672 | consumed samples: 7948800 | consumed tokens: 16279142400 | elapsed time per iteration (s): 0.77 | learning rate: 4.057E-05 | global batch size: 256 | lm loss: 2.086130E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.328 | TFLOPs: 20.17 | +31: iteration 31060/ 39672 | consumed samples: 7951360 | consumed tokens: 16284385280 | elapsed time per iteration (s): 0.77 | learning rate: 4.053E-05 | global batch size: 256 | lm loss: 2.081796E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.767 | TFLOPs: 20.01 | +31: iteration 31070/ 39672 | consumed samples: 7953920 | consumed tokens: 16289628160 | elapsed time per iteration (s): 0.77 | learning rate: 4.048E-05 | global batch size: 256 | lm loss: 2.131062E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.918 | TFLOPs: 20.08 | +31: iteration 31080/ 39672 | consumed samples: 7956480 | consumed tokens: 16294871040 | elapsed time per iteration (s): 0.75 | learning rate: 4.043E-05 | global batch size: 256 | lm loss: 2.111432E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.065 | TFLOPs: 20.69 | +31: iteration 31090/ 39672 | consumed samples: 7959040 | consumed tokens: 16300113920 | elapsed time per iteration (s): 0.77 | learning rate: 4.039E-05 | global batch size: 256 | lm loss: 2.115747E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.732 | TFLOPs: 20.07 | +31: iteration 31100/ 39672 | consumed samples: 7961600 | consumed tokens: 16305356800 | elapsed time per iteration (s): 0.74 | learning rate: 4.034E-05 | global batch size: 256 | lm loss: 2.081902E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.063 | TFLOPs: 20.88 | +31: iteration 31110/ 39672 | consumed samples: 7964160 | consumed tokens: 16310599680 | elapsed time per iteration (s): 0.82 | learning rate: 4.030E-05 | global batch size: 256 | lm loss: 2.105742E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.456 | TFLOPs: 18.96 | +31: iteration 31120/ 39672 | consumed samples: 7966720 | consumed tokens: 16315842560 | elapsed time per iteration (s): 0.81 | learning rate: 4.025E-05 | global batch size: 256 | lm loss: 2.086019E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.017 | TFLOPs: 19.06 | +31: iteration 31130/ 39672 | consumed samples: 7969280 | consumed tokens: 16321085440 | elapsed time per iteration (s): 0.82 | learning rate: 4.021E-05 | global batch size: 256 | lm loss: 2.122119E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.319 | TFLOPs: 18.95 | +31: iteration 31140/ 39672 | consumed samples: 7971840 | consumed tokens: 16326328320 | elapsed time per iteration (s): 0.79 | learning rate: 4.016E-05 | global batch size: 256 | lm loss: 2.094272E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.317 | TFLOPs: 19.56 | +31: iteration 31150/ 39672 | consumed samples: 7974400 | consumed tokens: 16331571200 | elapsed time per iteration (s): 0.78 | learning rate: 4.012E-05 | global batch size: 256 | lm loss: 2.077871E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.838 | TFLOPs: 19.95 | +31: iteration 31160/ 39672 | consumed samples: 7976960 | consumed tokens: 16336814080 | elapsed time per iteration (s): 0.76 | learning rate: 4.007E-05 | global batch size: 256 | lm loss: 2.085430E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.202 | TFLOPs: 20.34 | +31: iteration 31170/ 39672 | consumed samples: 7979520 | consumed tokens: 16342056960 | elapsed time per iteration (s): 0.75 | learning rate: 4.003E-05 | global batch size: 256 | lm loss: 2.094456E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.029 | TFLOPs: 20.69 | +31: iteration 31180/ 39672 | consumed samples: 7982080 | consumed tokens: 16347299840 | elapsed time per iteration (s): 0.79 | learning rate: 3.998E-05 | global batch size: 256 | lm loss: 2.107615E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.801 | TFLOPs: 19.65 | +31: iteration 31190/ 39672 | consumed samples: 7984640 | consumed tokens: 16352542720 | elapsed time per iteration (s): 0.75 | learning rate: 3.993E-05 | global batch size: 256 | lm loss: 2.085944E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.893 | TFLOPs: 20.62 | +31: iteration 31200/ 39672 | consumed samples: 7987200 | consumed tokens: 16357785600 | elapsed time per iteration (s): 0.88 | learning rate: 3.989E-05 | global batch size: 256 | lm loss: 2.093589E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 290.301 | TFLOPs: 17.56 | +31: iteration 31210/ 39672 | consumed samples: 7989760 | consumed tokens: 16363028480 | elapsed time per iteration (s): 0.78 | learning rate: 3.984E-05 | global batch size: 256 | lm loss: 2.085881E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.788 | TFLOPs: 19.77 | +31: iteration 31220/ 39672 | consumed samples: 7992320 | consumed tokens: 16368271360 | elapsed time per iteration (s): 0.84 | learning rate: 3.980E-05 | global batch size: 256 | lm loss: 2.109805E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.367 | TFLOPs: 18.47 | +31: iteration 31230/ 39672 | consumed samples: 7994880 | consumed tokens: 16373514240 | elapsed time per iteration (s): 0.81 | learning rate: 3.975E-05 | global batch size: 256 | lm loss: 2.086592E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.133 | TFLOPs: 19.00 | +31: iteration 31240/ 39672 | consumed samples: 7997440 | consumed tokens: 16378757120 | elapsed time per iteration (s): 0.87 | learning rate: 3.971E-05 | global batch size: 256 | lm loss: 2.108643E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.812 | TFLOPs: 17.90 | +31: iteration 31250/ 39672 | consumed samples: 8000000 | consumed tokens: 16384000000 | elapsed time per iteration (s): 0.84 | learning rate: 3.966E-05 | global batch size: 256 | lm loss: 2.083856E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.395 | TFLOPs: 18.42 | +31: iteration 31260/ 39672 | consumed samples: 8002560 | consumed tokens: 16389242880 | elapsed time per iteration (s): 0.89 | learning rate: 3.962E-05 | global batch size: 256 | lm loss: 2.064592E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 288.375 | TFLOPs: 17.45 | +31: iteration 31270/ 39672 | consumed samples: 8005120 | consumed tokens: 16394485760 | elapsed time per iteration (s): 0.79 | learning rate: 3.957E-05 | global batch size: 256 | lm loss: 2.062096E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.442 | TFLOPs: 19.57 | +31: iteration 31280/ 39672 | consumed samples: 8007680 | consumed tokens: 16399728640 | elapsed time per iteration (s): 0.80 | learning rate: 3.953E-05 | global batch size: 256 | lm loss: 2.072095E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.736 | TFLOPs: 19.40 | +31: iteration 31290/ 39672 | consumed samples: 8010240 | consumed tokens: 16404971520 | elapsed time per iteration (s): 0.82 | learning rate: 3.949E-05 | global batch size: 256 | lm loss: 2.066738E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.722 | TFLOPs: 18.98 | +31: iteration 31300/ 39672 | consumed samples: 8012800 | consumed tokens: 16410214400 | elapsed time per iteration (s): 0.79 | learning rate: 3.944E-05 | global batch size: 256 | lm loss: 2.097588E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.132 | TFLOPs: 19.67 | +31: iteration 31310/ 39672 | consumed samples: 8015360 | consumed tokens: 16415457280 | elapsed time per iteration (s): 0.80 | learning rate: 3.940E-05 | global batch size: 256 | lm loss: 2.058333E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.304 | TFLOPs: 19.32 | +31: iteration 31320/ 39672 | consumed samples: 8017920 | consumed tokens: 16420700160 | elapsed time per iteration (s): 0.83 | learning rate: 3.935E-05 | global batch size: 256 | lm loss: 2.108171E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.404 | TFLOPs: 18.60 | +31: iteration 31330/ 39672 | consumed samples: 8020480 | consumed tokens: 16425943040 | elapsed time per iteration (s): 0.85 | learning rate: 3.931E-05 | global batch size: 256 | lm loss: 2.074949E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.049 | TFLOPs: 18.15 | +31: iteration 31340/ 39672 | consumed samples: 8023040 | consumed tokens: 16431185920 | elapsed time per iteration (s): 0.81 | learning rate: 3.926E-05 | global batch size: 256 | lm loss: 2.113636E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.177 | TFLOPs: 19.19 | +31: iteration 31350/ 39672 | consumed samples: 8025600 | consumed tokens: 16436428800 | elapsed time per iteration (s): 0.77 | learning rate: 3.922E-05 | global batch size: 256 | lm loss: 2.077999E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.281 | TFLOPs: 20.04 | +31: iteration 31360/ 39672 | consumed samples: 8028160 | consumed tokens: 16441671680 | elapsed time per iteration (s): 0.80 | learning rate: 3.917E-05 | global batch size: 256 | lm loss: 2.113559E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.215 | TFLOPs: 19.25 | +31: iteration 31370/ 39672 | consumed samples: 8030720 | consumed tokens: 16446914560 | elapsed time per iteration (s): 0.80 | learning rate: 3.913E-05 | global batch size: 256 | lm loss: 2.075473E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.473 | TFLOPs: 19.27 | +31: iteration 31380/ 39672 | consumed samples: 8033280 | consumed tokens: 16452157440 | elapsed time per iteration (s): 0.81 | learning rate: 3.908E-05 | global batch size: 256 | lm loss: 2.074502E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.856 | TFLOPs: 19.17 | +31: iteration 31390/ 39672 | consumed samples: 8035840 | consumed tokens: 16457400320 | elapsed time per iteration (s): 0.81 | learning rate: 3.904E-05 | global batch size: 256 | lm loss: 2.109663E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.272 | TFLOPs: 19.07 | +31: iteration 31400/ 39672 | consumed samples: 8038400 | consumed tokens: 16462643200 | elapsed time per iteration (s): 0.77 | learning rate: 3.900E-05 | global batch size: 256 | lm loss: 2.085376E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.346 | TFLOPs: 19.99 | +31: iteration 31410/ 39672 | consumed samples: 8040960 | consumed tokens: 16467886080 | elapsed time per iteration (s): 0.83 | learning rate: 3.895E-05 | global batch size: 256 | lm loss: 2.091948E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.778 | TFLOPs: 18.62 | +31: iteration 31420/ 39672 | consumed samples: 8043520 | consumed tokens: 16473128960 | elapsed time per iteration (s): 0.81 | learning rate: 3.891E-05 | global batch size: 256 | lm loss: 2.073216E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.211 | TFLOPs: 19.13 | +31: iteration 31430/ 39672 | consumed samples: 8046080 | consumed tokens: 16478371840 | elapsed time per iteration (s): 0.81 | learning rate: 3.886E-05 | global batch size: 256 | lm loss: 2.109748E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.726 | TFLOPs: 19.04 | +31: iteration 31440/ 39672 | consumed samples: 8048640 | consumed tokens: 16483614720 | elapsed time per iteration (s): 0.81 | learning rate: 3.882E-05 | global batch size: 256 | lm loss: 2.096711E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.553 | TFLOPs: 19.15 | +31: iteration 31450/ 39672 | consumed samples: 8051200 | consumed tokens: 16488857600 | elapsed time per iteration (s): 0.81 | learning rate: 3.878E-05 | global batch size: 256 | lm loss: 2.070924E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.136 | TFLOPs: 19.19 | +31: iteration 31460/ 39672 | consumed samples: 8053760 | consumed tokens: 16494100480 | elapsed time per iteration (s): 0.82 | learning rate: 3.873E-05 | global batch size: 256 | lm loss: 2.117874E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.827 | TFLOPs: 18.86 | +31: iteration 31470/ 39672 | consumed samples: 8056320 | consumed tokens: 16499343360 | elapsed time per iteration (s): 0.83 | learning rate: 3.869E-05 | global batch size: 256 | lm loss: 2.122708E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.892 | TFLOPs: 18.69 | +31: iteration 31480/ 39672 | consumed samples: 8058880 | consumed tokens: 16504586240 | elapsed time per iteration (s): 0.84 | learning rate: 3.864E-05 | global batch size: 256 | lm loss: 2.098683E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.550 | TFLOPs: 18.42 | +31: iteration 31490/ 39672 | consumed samples: 8061440 | consumed tokens: 16509829120 | elapsed time per iteration (s): 0.81 | learning rate: 3.860E-05 | global batch size: 256 | lm loss: 2.076027E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.274 | TFLOPs: 19.13 | +31: iteration 31500/ 39672 | consumed samples: 8064000 | consumed tokens: 16515072000 | elapsed time per iteration (s): 0.81 | learning rate: 3.856E-05 | global batch size: 256 | lm loss: 2.086356E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.215 | TFLOPs: 19.01 | +31: iteration 31510/ 39672 | consumed samples: 8066560 | consumed tokens: 16520314880 | elapsed time per iteration (s): 0.85 | learning rate: 3.851E-05 | global batch size: 256 | lm loss: 2.128315E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.562 | TFLOPs: 18.24 | +31: iteration 31520/ 39672 | consumed samples: 8069120 | consumed tokens: 16525557760 | elapsed time per iteration (s): 0.84 | learning rate: 3.847E-05 | global batch size: 256 | lm loss: 2.050714E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.803 | TFLOPs: 18.38 | +31: iteration 31530/ 39672 | consumed samples: 8071680 | consumed tokens: 16530800640 | elapsed time per iteration (s): 0.84 | learning rate: 3.842E-05 | global batch size: 256 | lm loss: 2.066815E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.287 | TFLOPs: 18.41 | +31: iteration 31540/ 39672 | consumed samples: 8074240 | consumed tokens: 16536043520 | elapsed time per iteration (s): 0.81 | learning rate: 3.838E-05 | global batch size: 256 | lm loss: 2.088506E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.843 | TFLOPs: 19.11 | +31: iteration 31550/ 39672 | consumed samples: 8076800 | consumed tokens: 16541286400 | elapsed time per iteration (s): 0.85 | learning rate: 3.834E-05 | global batch size: 256 | lm loss: 2.092336E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.269 | TFLOPs: 18.23 | +31: iteration 31560/ 39672 | consumed samples: 8079360 | consumed tokens: 16546529280 | elapsed time per iteration (s): 0.80 | learning rate: 3.829E-05 | global batch size: 256 | lm loss: 2.095148E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.287 | TFLOPs: 19.32 | +31: iteration 31570/ 39672 | consumed samples: 8081920 | consumed tokens: 16551772160 | elapsed time per iteration (s): 0.81 | learning rate: 3.825E-05 | global batch size: 256 | lm loss: 2.081449E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.853 | TFLOPs: 19.23 | +31: iteration 31580/ 39672 | consumed samples: 8084480 | consumed tokens: 16557015040 | elapsed time per iteration (s): 0.78 | learning rate: 3.821E-05 | global batch size: 256 | lm loss: 2.099426E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.048 | TFLOPs: 19.79 | +31: iteration 31590/ 39672 | consumed samples: 8087040 | consumed tokens: 16562257920 | elapsed time per iteration (s): 0.80 | learning rate: 3.816E-05 | global batch size: 256 | lm loss: 2.074745E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.217 | TFLOPs: 19.31 | +31: iteration 31600/ 39672 | consumed samples: 8089600 | consumed tokens: 16567500800 | elapsed time per iteration (s): 0.80 | learning rate: 3.812E-05 | global batch size: 256 | lm loss: 2.071226E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.082 | TFLOPs: 19.30 | +31: iteration 31610/ 39672 | consumed samples: 8092160 | consumed tokens: 16572743680 | elapsed time per iteration (s): 0.80 | learning rate: 3.808E-05 | global batch size: 256 | lm loss: 2.072384E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.766 | TFLOPs: 19.35 | +31: iteration 31620/ 39672 | consumed samples: 8094720 | consumed tokens: 16577986560 | elapsed time per iteration (s): 0.74 | learning rate: 3.803E-05 | global batch size: 256 | lm loss: 2.099346E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.438 | TFLOPs: 20.90 | +31: iteration 31630/ 39672 | consumed samples: 8097280 | consumed tokens: 16583229440 | elapsed time per iteration (s): 0.77 | learning rate: 3.799E-05 | global batch size: 256 | lm loss: 2.089185E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.054 | TFLOPs: 20.15 | +31: iteration 31640/ 39672 | consumed samples: 8099840 | consumed tokens: 16588472320 | elapsed time per iteration (s): 0.75 | learning rate: 3.795E-05 | global batch size: 256 | lm loss: 2.096372E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.993 | TFLOPs: 20.63 | +31: iteration 31650/ 39672 | consumed samples: 8102400 | consumed tokens: 16593715200 | elapsed time per iteration (s): 0.77 | learning rate: 3.790E-05 | global batch size: 256 | lm loss: 2.091109E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.354 | TFLOPs: 20.23 | +31: iteration 31660/ 39672 | consumed samples: 8104960 | consumed tokens: 16598958080 | elapsed time per iteration (s): 0.79 | learning rate: 3.786E-05 | global batch size: 256 | lm loss: 2.075357E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.642 | TFLOPs: 19.70 | +31: iteration 31670/ 39672 | consumed samples: 8107520 | consumed tokens: 16604200960 | elapsed time per iteration (s): 0.78 | learning rate: 3.782E-05 | global batch size: 256 | lm loss: 2.096969E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.254 | TFLOPs: 19.80 | +31: iteration 31680/ 39672 | consumed samples: 8110080 | consumed tokens: 16609443840 | elapsed time per iteration (s): 0.77 | learning rate: 3.778E-05 | global batch size: 256 | lm loss: 2.081629E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.138 | TFLOPs: 20.21 | +31: iteration 31690/ 39672 | consumed samples: 8112640 | consumed tokens: 16614686720 | elapsed time per iteration (s): 0.79 | learning rate: 3.773E-05 | global batch size: 256 | lm loss: 2.102456E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.228 | TFLOPs: 19.61 | +31: iteration 31700/ 39672 | consumed samples: 8115200 | consumed tokens: 16619929600 | elapsed time per iteration (s): 0.76 | learning rate: 3.769E-05 | global batch size: 256 | lm loss: 2.066947E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.372 | TFLOPs: 20.41 | +31: iteration 31710/ 39672 | consumed samples: 8117760 | consumed tokens: 16625172480 | elapsed time per iteration (s): 0.75 | learning rate: 3.765E-05 | global batch size: 256 | lm loss: 2.086825E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.678 | TFLOPs: 20.67 | +31: iteration 31720/ 39672 | consumed samples: 8120320 | consumed tokens: 16630415360 | elapsed time per iteration (s): 0.75 | learning rate: 3.760E-05 | global batch size: 256 | lm loss: 2.114922E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.179 | TFLOPs: 20.64 | +31: iteration 31730/ 39672 | consumed samples: 8122880 | consumed tokens: 16635658240 | elapsed time per iteration (s): 0.79 | learning rate: 3.756E-05 | global batch size: 256 | lm loss: 2.107263E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.523 | TFLOPs: 19.51 | +31: iteration 31740/ 39672 | consumed samples: 8125440 | consumed tokens: 16640901120 | elapsed time per iteration (s): 0.77 | learning rate: 3.752E-05 | global batch size: 256 | lm loss: 2.106827E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.767 | TFLOPs: 20.07 | +31: iteration 31750/ 39672 | consumed samples: 8128000 | consumed tokens: 16646144000 | elapsed time per iteration (s): 0.77 | learning rate: 3.748E-05 | global batch size: 256 | lm loss: 2.079228E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.793 | TFLOPs: 20.07 | +31: iteration 31760/ 39672 | consumed samples: 8130560 | consumed tokens: 16651386880 | elapsed time per iteration (s): 0.71 | learning rate: 3.743E-05 | global batch size: 256 | lm loss: 2.115432E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 361.136 | TFLOPs: 21.85 | +31: iteration 31770/ 39672 | consumed samples: 8133120 | consumed tokens: 16656629760 | elapsed time per iteration (s): 0.76 | learning rate: 3.739E-05 | global batch size: 256 | lm loss: 2.084486E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.787 | TFLOPs: 20.37 | +31: iteration 31780/ 39672 | consumed samples: 8135680 | consumed tokens: 16661872640 | elapsed time per iteration (s): 0.80 | learning rate: 3.735E-05 | global batch size: 256 | lm loss: 2.097407E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.288 | TFLOPs: 19.38 | +31: iteration 31790/ 39672 | consumed samples: 8138240 | consumed tokens: 16667115520 | elapsed time per iteration (s): 0.76 | learning rate: 3.731E-05 | global batch size: 256 | lm loss: 2.097237E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.459 | TFLOPs: 20.42 | +31: iteration 31800/ 39672 | consumed samples: 8140800 | consumed tokens: 16672358400 | elapsed time per iteration (s): 0.82 | learning rate: 3.726E-05 | global batch size: 256 | lm loss: 2.094736E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.035 | TFLOPs: 18.94 | +31: iteration 31810/ 39672 | consumed samples: 8143360 | consumed tokens: 16677601280 | elapsed time per iteration (s): 0.79 | learning rate: 3.722E-05 | global batch size: 256 | lm loss: 2.082932E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.520 | TFLOPs: 19.69 | +31: iteration 31820/ 39672 | consumed samples: 8145920 | consumed tokens: 16682844160 | elapsed time per iteration (s): 0.77 | learning rate: 3.718E-05 | global batch size: 256 | lm loss: 2.092776E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.210 | TFLOPs: 20.04 | +31: iteration 31830/ 39672 | consumed samples: 8148480 | consumed tokens: 16688087040 | elapsed time per iteration (s): 0.78 | learning rate: 3.714E-05 | global batch size: 256 | lm loss: 2.115211E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.347 | TFLOPs: 19.86 | +31: iteration 31840/ 39672 | consumed samples: 8151040 | consumed tokens: 16693329920 | elapsed time per iteration (s): 0.74 | learning rate: 3.709E-05 | global batch size: 256 | lm loss: 2.084563E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.154 | TFLOPs: 21.06 | +31: iteration 31850/ 39672 | consumed samples: 8153600 | consumed tokens: 16698572800 | elapsed time per iteration (s): 0.79 | learning rate: 3.705E-05 | global batch size: 256 | lm loss: 2.091285E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.114 | TFLOPs: 19.67 | +31: iteration 31860/ 39672 | consumed samples: 8156160 | consumed tokens: 16703815680 | elapsed time per iteration (s): 0.73 | learning rate: 3.701E-05 | global batch size: 256 | lm loss: 2.059395E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.526 | TFLOPs: 21.15 | +31: iteration 31870/ 39672 | consumed samples: 8158720 | consumed tokens: 16709058560 | elapsed time per iteration (s): 0.78 | learning rate: 3.697E-05 | global batch size: 256 | lm loss: 2.088228E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.358 | TFLOPs: 19.86 | +31: iteration 31880/ 39672 | consumed samples: 8161280 | consumed tokens: 16714301440 | elapsed time per iteration (s): 0.79 | learning rate: 3.693E-05 | global batch size: 256 | lm loss: 2.081234E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.288 | TFLOPs: 19.68 | +31: iteration 31890/ 39672 | consumed samples: 8163840 | consumed tokens: 16719544320 | elapsed time per iteration (s): 0.77 | learning rate: 3.688E-05 | global batch size: 256 | lm loss: 2.056447E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.865 | TFLOPs: 20.02 | +31: iteration 31900/ 39672 | consumed samples: 8166400 | consumed tokens: 16724787200 | elapsed time per iteration (s): 0.77 | learning rate: 3.684E-05 | global batch size: 256 | lm loss: 2.115500E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.320 | TFLOPs: 20.04 | +31: iteration 31910/ 39672 | consumed samples: 8168960 | consumed tokens: 16730030080 | elapsed time per iteration (s): 0.76 | learning rate: 3.680E-05 | global batch size: 256 | lm loss: 2.095629E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.992 | TFLOPs: 20.27 | +31: iteration 31920/ 39672 | consumed samples: 8171520 | consumed tokens: 16735272960 | elapsed time per iteration (s): 0.72 | learning rate: 3.676E-05 | global batch size: 256 | lm loss: 2.060645E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.476 | TFLOPs: 21.51 | +31: iteration 31930/ 39672 | consumed samples: 8174080 | consumed tokens: 16740515840 | elapsed time per iteration (s): 0.75 | learning rate: 3.672E-05 | global batch size: 256 | lm loss: 2.087171E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.293 | TFLOPs: 20.59 | +31: iteration 31940/ 39672 | consumed samples: 8176640 | consumed tokens: 16745758720 | elapsed time per iteration (s): 0.80 | learning rate: 3.667E-05 | global batch size: 256 | lm loss: 2.101954E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.803 | TFLOPs: 19.41 | +31: iteration 31950/ 39672 | consumed samples: 8179200 | consumed tokens: 16751001600 | elapsed time per iteration (s): 0.81 | learning rate: 3.663E-05 | global batch size: 256 | lm loss: 2.071883E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.440 | TFLOPs: 19.02 | +31: iteration 31960/ 39672 | consumed samples: 8181760 | consumed tokens: 16756244480 | elapsed time per iteration (s): 0.82 | learning rate: 3.659E-05 | global batch size: 256 | lm loss: 2.055136E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.288 | TFLOPs: 18.89 | +31: iteration 31970/ 39672 | consumed samples: 8184320 | consumed tokens: 16761487360 | elapsed time per iteration (s): 0.78 | learning rate: 3.655E-05 | global batch size: 256 | lm loss: 2.104933E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.165 | TFLOPs: 19.97 | +31: iteration 31980/ 39672 | consumed samples: 8186880 | consumed tokens: 16766730240 | elapsed time per iteration (s): 0.79 | learning rate: 3.651E-05 | global batch size: 256 | lm loss: 2.086462E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.607 | TFLOPs: 19.64 | +31: iteration 31990/ 39672 | consumed samples: 8189440 | consumed tokens: 16771973120 | elapsed time per iteration (s): 0.82 | learning rate: 3.647E-05 | global batch size: 256 | lm loss: 2.087455E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.213 | TFLOPs: 18.83 | + 0: [2022-11-30 16:16:49,478] [INFO] [logging.py:68:log_dist] [Rank 0] step=32000, skipped=0, lr=[3.6424555906094434e-05, 3.6424555906094434e-05, 3.6424555906094434e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 32000/ 39672 | consumed samples: 8192000 | consumed tokens: 16777216000 | elapsed time per iteration (s): 0.85 | learning rate: 3.642E-05 | global batch size: 256 | lm loss: 2.066677E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.541 | TFLOPs: 18.18 | + 0: steps: 32000 loss: 1.9912 iter time (s): 0.786 samples/sec: 325.556 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 32000 | lm loss value: 1.959266E+00 | lm loss PPL: 7.094119E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 32010/ 39672 | consumed samples: 8194560 | consumed tokens: 16782458880 | elapsed time per iteration (s): 0.81 | learning rate: 3.638E-05 | global batch size: 256 | lm loss: 2.085884E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.066 | TFLOPs: 19.06 | +31: iteration 32020/ 39672 | consumed samples: 8197120 | consumed tokens: 16787701760 | elapsed time per iteration (s): 0.74 | learning rate: 3.634E-05 | global batch size: 256 | lm loss: 2.067000E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.199 | TFLOPs: 20.88 | +31: iteration 32030/ 39672 | consumed samples: 8199680 | consumed tokens: 16792944640 | elapsed time per iteration (s): 0.79 | learning rate: 3.630E-05 | global batch size: 256 | lm loss: 2.092467E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.663 | TFLOPs: 19.52 | +31: iteration 32040/ 39672 | consumed samples: 8202240 | consumed tokens: 16798187520 | elapsed time per iteration (s): 0.75 | learning rate: 3.626E-05 | global batch size: 256 | lm loss: 2.115704E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.791 | TFLOPs: 20.74 | +31: iteration 32050/ 39672 | consumed samples: 8204800 | consumed tokens: 16803430400 | elapsed time per iteration (s): 0.77 | learning rate: 3.622E-05 | global batch size: 256 | lm loss: 2.116282E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.945 | TFLOPs: 20.02 | +31: iteration 32060/ 39672 | consumed samples: 8207360 | consumed tokens: 16808673280 | elapsed time per iteration (s): 0.75 | learning rate: 3.618E-05 | global batch size: 256 | lm loss: 2.078921E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.896 | TFLOPs: 20.62 | +31: iteration 32070/ 39672 | consumed samples: 8209920 | consumed tokens: 16813916160 | elapsed time per iteration (s): 0.81 | learning rate: 3.614E-05 | global batch size: 256 | lm loss: 2.089968E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.047 | TFLOPs: 19.12 | +31: iteration 32080/ 39672 | consumed samples: 8212480 | consumed tokens: 16819159040 | elapsed time per iteration (s): 0.74 | learning rate: 3.609E-05 | global batch size: 256 | lm loss: 2.110894E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.651 | TFLOPs: 20.97 | +31: iteration 32090/ 39672 | consumed samples: 8215040 | consumed tokens: 16824401920 | elapsed time per iteration (s): 0.78 | learning rate: 3.605E-05 | global batch size: 256 | lm loss: 2.106805E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.852 | TFLOPs: 19.89 | +31: iteration 32100/ 39672 | consumed samples: 8217600 | consumed tokens: 16829644800 | elapsed time per iteration (s): 0.84 | learning rate: 3.601E-05 | global batch size: 256 | lm loss: 2.095645E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.195 | TFLOPs: 18.34 | +31: iteration 32110/ 39672 | consumed samples: 8220160 | consumed tokens: 16834887680 | elapsed time per iteration (s): 0.80 | learning rate: 3.597E-05 | global batch size: 256 | lm loss: 2.087099E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.657 | TFLOPs: 19.28 | +31: iteration 32120/ 39672 | consumed samples: 8222720 | consumed tokens: 16840130560 | elapsed time per iteration (s): 0.79 | learning rate: 3.593E-05 | global batch size: 256 | lm loss: 2.083985E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.073 | TFLOPs: 19.67 | +31: iteration 32130/ 39672 | consumed samples: 8225280 | consumed tokens: 16845373440 | elapsed time per iteration (s): 0.74 | learning rate: 3.589E-05 | global batch size: 256 | lm loss: 2.130386E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.460 | TFLOPs: 20.96 | +31: iteration 32140/ 39672 | consumed samples: 8227840 | consumed tokens: 16850616320 | elapsed time per iteration (s): 0.74 | learning rate: 3.585E-05 | global batch size: 256 | lm loss: 2.053010E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.965 | TFLOPs: 20.81 | +31: iteration 32150/ 39672 | consumed samples: 8230400 | consumed tokens: 16855859200 | elapsed time per iteration (s): 0.78 | learning rate: 3.581E-05 | global batch size: 256 | lm loss: 2.075258E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.300 | TFLOPs: 19.74 | +31: iteration 32160/ 39672 | consumed samples: 8232960 | consumed tokens: 16861102080 | elapsed time per iteration (s): 0.76 | learning rate: 3.577E-05 | global batch size: 256 | lm loss: 2.109406E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.773 | TFLOPs: 20.43 | +31: iteration 32170/ 39672 | consumed samples: 8235520 | consumed tokens: 16866344960 | elapsed time per iteration (s): 0.78 | learning rate: 3.573E-05 | global batch size: 256 | lm loss: 2.072913E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.560 | TFLOPs: 19.88 | +31: iteration 32180/ 39672 | consumed samples: 8238080 | consumed tokens: 16871587840 | elapsed time per iteration (s): 0.79 | learning rate: 3.569E-05 | global batch size: 256 | lm loss: 2.080143E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.659 | TFLOPs: 19.70 | +31: iteration 32190/ 39672 | consumed samples: 8240640 | consumed tokens: 16876830720 | elapsed time per iteration (s): 0.76 | learning rate: 3.565E-05 | global batch size: 256 | lm loss: 2.085478E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.121 | TFLOPs: 20.39 | +31: iteration 32200/ 39672 | consumed samples: 8243200 | consumed tokens: 16882073600 | elapsed time per iteration (s): 0.73 | learning rate: 3.560E-05 | global batch size: 256 | lm loss: 2.099890E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.695 | TFLOPs: 21.16 | +31: iteration 32210/ 39672 | consumed samples: 8245760 | consumed tokens: 16887316480 | elapsed time per iteration (s): 0.72 | learning rate: 3.556E-05 | global batch size: 256 | lm loss: 2.089478E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.124 | TFLOPs: 21.48 | +31: iteration 32220/ 39672 | consumed samples: 8248320 | consumed tokens: 16892559360 | elapsed time per iteration (s): 0.81 | learning rate: 3.552E-05 | global batch size: 256 | lm loss: 2.078933E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.570 | TFLOPs: 19.21 | +31: iteration 32230/ 39672 | consumed samples: 8250880 | consumed tokens: 16897802240 | elapsed time per iteration (s): 0.75 | learning rate: 3.548E-05 | global batch size: 256 | lm loss: 2.072592E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.326 | TFLOPs: 20.65 | +31: iteration 32240/ 39672 | consumed samples: 8253440 | consumed tokens: 16903045120 | elapsed time per iteration (s): 0.75 | learning rate: 3.544E-05 | global batch size: 256 | lm loss: 2.104694E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.837 | TFLOPs: 20.62 | +31: iteration 32250/ 39672 | consumed samples: 8256000 | consumed tokens: 16908288000 | elapsed time per iteration (s): 0.72 | learning rate: 3.540E-05 | global batch size: 256 | lm loss: 2.091836E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.184 | TFLOPs: 21.49 | +31: iteration 32260/ 39672 | consumed samples: 8258560 | consumed tokens: 16913530880 | elapsed time per iteration (s): 0.74 | learning rate: 3.536E-05 | global batch size: 256 | lm loss: 2.162146E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.681 | TFLOPs: 20.91 | +31: iteration 32270/ 39672 | consumed samples: 8261120 | consumed tokens: 16918773760 | elapsed time per iteration (s): 0.74 | learning rate: 3.532E-05 | global batch size: 256 | lm loss: 2.096535E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.885 | TFLOPs: 20.93 | +31: iteration 32280/ 39672 | consumed samples: 8263680 | consumed tokens: 16924016640 | elapsed time per iteration (s): 0.79 | learning rate: 3.528E-05 | global batch size: 256 | lm loss: 2.072301E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.560 | TFLOPs: 19.64 | +31: iteration 32290/ 39672 | consumed samples: 8266240 | consumed tokens: 16929259520 | elapsed time per iteration (s): 0.81 | learning rate: 3.524E-05 | global batch size: 256 | lm loss: 2.105363E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.880 | TFLOPs: 19.11 | +31: iteration 32300/ 39672 | consumed samples: 8268800 | consumed tokens: 16934502400 | elapsed time per iteration (s): 0.76 | learning rate: 3.520E-05 | global batch size: 256 | lm loss: 2.088237E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.931 | TFLOPs: 20.32 | +31: iteration 32310/ 39672 | consumed samples: 8271360 | consumed tokens: 16939745280 | elapsed time per iteration (s): 0.75 | learning rate: 3.516E-05 | global batch size: 256 | lm loss: 2.090187E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.425 | TFLOPs: 20.66 | +31: iteration 32320/ 39672 | consumed samples: 8273920 | consumed tokens: 16944988160 | elapsed time per iteration (s): 0.77 | learning rate: 3.512E-05 | global batch size: 256 | lm loss: 2.111879E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.202 | TFLOPs: 20.10 | +31: iteration 32330/ 39672 | consumed samples: 8276480 | consumed tokens: 16950231040 | elapsed time per iteration (s): 0.80 | learning rate: 3.508E-05 | global batch size: 256 | lm loss: 2.109795E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.303 | TFLOPs: 19.38 | +31: iteration 32340/ 39672 | consumed samples: 8279040 | consumed tokens: 16955473920 | elapsed time per iteration (s): 0.83 | learning rate: 3.504E-05 | global batch size: 256 | lm loss: 2.111110E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.353 | TFLOPs: 18.59 | +31: iteration 32350/ 39672 | consumed samples: 8281600 | consumed tokens: 16960716800 | elapsed time per iteration (s): 0.82 | learning rate: 3.500E-05 | global batch size: 256 | lm loss: 2.104973E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.938 | TFLOPs: 18.99 | +31: iteration 32360/ 39672 | consumed samples: 8284160 | consumed tokens: 16965959680 | elapsed time per iteration (s): 0.79 | learning rate: 3.496E-05 | global batch size: 256 | lm loss: 2.079958E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.588 | TFLOPs: 19.64 | +31: iteration 32370/ 39672 | consumed samples: 8286720 | consumed tokens: 16971202560 | elapsed time per iteration (s): 0.81 | learning rate: 3.492E-05 | global batch size: 256 | lm loss: 2.087198E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.165 | TFLOPs: 19.01 | +31: iteration 32380/ 39672 | consumed samples: 8289280 | consumed tokens: 16976445440 | elapsed time per iteration (s): 0.79 | learning rate: 3.488E-05 | global batch size: 256 | lm loss: 2.081631E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.902 | TFLOPs: 19.66 | +31: iteration 32390/ 39672 | consumed samples: 8291840 | consumed tokens: 16981688320 | elapsed time per iteration (s): 0.79 | learning rate: 3.484E-05 | global batch size: 256 | lm loss: 2.084643E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.945 | TFLOPs: 19.54 | +31: iteration 32400/ 39672 | consumed samples: 8294400 | consumed tokens: 16986931200 | elapsed time per iteration (s): 0.79 | learning rate: 3.480E-05 | global batch size: 256 | lm loss: 2.069891E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.413 | TFLOPs: 19.51 | +31: iteration 32410/ 39672 | consumed samples: 8296960 | consumed tokens: 16992174080 | elapsed time per iteration (s): 0.74 | learning rate: 3.476E-05 | global batch size: 256 | lm loss: 2.075585E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.794 | TFLOPs: 21.04 | +31: iteration 32420/ 39672 | consumed samples: 8299520 | consumed tokens: 16997416960 | elapsed time per iteration (s): 0.74 | learning rate: 3.473E-05 | global batch size: 256 | lm loss: 2.096373E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.010 | TFLOPs: 20.99 | +31: iteration 32430/ 39672 | consumed samples: 8302080 | consumed tokens: 17002659840 | elapsed time per iteration (s): 0.77 | learning rate: 3.469E-05 | global batch size: 256 | lm loss: 2.083448E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.435 | TFLOPs: 20.05 | +31: iteration 32440/ 39672 | consumed samples: 8304640 | consumed tokens: 17007902720 | elapsed time per iteration (s): 0.73 | learning rate: 3.465E-05 | global batch size: 256 | lm loss: 2.108908E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 348.787 | TFLOPs: 21.10 | +31: iteration 32450/ 39672 | consumed samples: 8307200 | consumed tokens: 17013145600 | elapsed time per iteration (s): 0.77 | learning rate: 3.461E-05 | global batch size: 256 | lm loss: 2.070620E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.401 | TFLOPs: 20.11 | +31: iteration 32460/ 39672 | consumed samples: 8309760 | consumed tokens: 17018388480 | elapsed time per iteration (s): 0.79 | learning rate: 3.457E-05 | global batch size: 256 | lm loss: 2.085899E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.494 | TFLOPs: 19.57 | +31: iteration 32470/ 39672 | consumed samples: 8312320 | consumed tokens: 17023631360 | elapsed time per iteration (s): 0.75 | learning rate: 3.453E-05 | global batch size: 256 | lm loss: 2.095432E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.668 | TFLOPs: 20.61 | +31: iteration 32480/ 39672 | consumed samples: 8314880 | consumed tokens: 17028874240 | elapsed time per iteration (s): 0.76 | learning rate: 3.449E-05 | global batch size: 256 | lm loss: 2.084888E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.917 | TFLOPs: 20.32 | +31: iteration 32490/ 39672 | consumed samples: 8317440 | consumed tokens: 17034117120 | elapsed time per iteration (s): 0.74 | learning rate: 3.445E-05 | global batch size: 256 | lm loss: 2.040588E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.369 | TFLOPs: 20.89 | +31: iteration 32500/ 39672 | consumed samples: 8320000 | consumed tokens: 17039360000 | elapsed time per iteration (s): 0.80 | learning rate: 3.441E-05 | global batch size: 256 | lm loss: 2.067173E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.166 | TFLOPs: 19.37 | +31: iteration 32510/ 39672 | consumed samples: 8322560 | consumed tokens: 17044602880 | elapsed time per iteration (s): 0.78 | learning rate: 3.437E-05 | global batch size: 256 | lm loss: 2.069140E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.316 | TFLOPs: 19.92 | +31: iteration 32520/ 39672 | consumed samples: 8325120 | consumed tokens: 17049845760 | elapsed time per iteration (s): 0.85 | learning rate: 3.433E-05 | global batch size: 256 | lm loss: 2.085548E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.732 | TFLOPs: 18.19 | +31: iteration 32530/ 39672 | consumed samples: 8327680 | consumed tokens: 17055088640 | elapsed time per iteration (s): 0.74 | learning rate: 3.429E-05 | global batch size: 256 | lm loss: 2.072613E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.551 | TFLOPs: 20.90 | +31: iteration 32540/ 39672 | consumed samples: 8330240 | consumed tokens: 17060331520 | elapsed time per iteration (s): 0.81 | learning rate: 3.426E-05 | global batch size: 256 | lm loss: 2.073002E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.102 | TFLOPs: 19.12 | +31: iteration 32550/ 39672 | consumed samples: 8332800 | consumed tokens: 17065574400 | elapsed time per iteration (s): 0.83 | learning rate: 3.422E-05 | global batch size: 256 | lm loss: 2.108007E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.198 | TFLOPs: 18.58 | +31: iteration 32560/ 39672 | consumed samples: 8335360 | consumed tokens: 17070817280 | elapsed time per iteration (s): 0.83 | learning rate: 3.418E-05 | global batch size: 256 | lm loss: 2.088449E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.962 | TFLOPs: 18.57 | +31: iteration 32570/ 39672 | consumed samples: 8337920 | consumed tokens: 17076060160 | elapsed time per iteration (s): 0.81 | learning rate: 3.414E-05 | global batch size: 256 | lm loss: 2.076478E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.851 | TFLOPs: 19.05 | +31: iteration 32580/ 39672 | consumed samples: 8340480 | consumed tokens: 17081303040 | elapsed time per iteration (s): 0.87 | learning rate: 3.410E-05 | global batch size: 256 | lm loss: 2.071193E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 293.596 | TFLOPs: 17.76 | +31: iteration 32590/ 39672 | consumed samples: 8343040 | consumed tokens: 17086545920 | elapsed time per iteration (s): 0.78 | learning rate: 3.406E-05 | global batch size: 256 | lm loss: 2.092374E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.129 | TFLOPs: 19.97 | +31: iteration 32600/ 39672 | consumed samples: 8345600 | consumed tokens: 17091788800 | elapsed time per iteration (s): 0.78 | learning rate: 3.402E-05 | global batch size: 256 | lm loss: 2.079105E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.188 | TFLOPs: 19.73 | +31: iteration 32610/ 39672 | consumed samples: 8348160 | consumed tokens: 17097031680 | elapsed time per iteration (s): 0.77 | learning rate: 3.398E-05 | global batch size: 256 | lm loss: 2.047600E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.965 | TFLOPs: 20.08 | +31: iteration 32620/ 39672 | consumed samples: 8350720 | consumed tokens: 17102274560 | elapsed time per iteration (s): 0.77 | learning rate: 3.395E-05 | global batch size: 256 | lm loss: 2.087237E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.345 | TFLOPs: 20.11 | +31: iteration 32630/ 39672 | consumed samples: 8353280 | consumed tokens: 17107517440 | elapsed time per iteration (s): 0.74 | learning rate: 3.391E-05 | global batch size: 256 | lm loss: 2.068514E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.936 | TFLOPs: 21.05 | +31: iteration 32640/ 39672 | consumed samples: 8355840 | consumed tokens: 17112760320 | elapsed time per iteration (s): 0.83 | learning rate: 3.387E-05 | global batch size: 256 | lm loss: 2.071852E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.236 | TFLOPs: 18.65 | +31: iteration 32650/ 39672 | consumed samples: 8358400 | consumed tokens: 17118003200 | elapsed time per iteration (s): 0.78 | learning rate: 3.383E-05 | global batch size: 256 | lm loss: 2.054852E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.724 | TFLOPs: 19.95 | +31: iteration 32660/ 39672 | consumed samples: 8360960 | consumed tokens: 17123246080 | elapsed time per iteration (s): 0.75 | learning rate: 3.379E-05 | global batch size: 256 | lm loss: 2.049651E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.986 | TFLOPs: 20.69 | +31: iteration 32670/ 39672 | consumed samples: 8363520 | consumed tokens: 17128488960 | elapsed time per iteration (s): 0.82 | learning rate: 3.375E-05 | global batch size: 256 | lm loss: 2.093840E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.189 | TFLOPs: 18.89 | +31: iteration 32680/ 39672 | consumed samples: 8366080 | consumed tokens: 17133731840 | elapsed time per iteration (s): 0.70 | learning rate: 3.372E-05 | global batch size: 256 | lm loss: 2.091846E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 363.139 | TFLOPs: 21.97 | +31: iteration 32690/ 39672 | consumed samples: 8368640 | consumed tokens: 17138974720 | elapsed time per iteration (s): 0.77 | learning rate: 3.368E-05 | global batch size: 256 | lm loss: 2.078121E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.247 | TFLOPs: 20.10 | +31: iteration 32700/ 39672 | consumed samples: 8371200 | consumed tokens: 17144217600 | elapsed time per iteration (s): 0.77 | learning rate: 3.364E-05 | global batch size: 256 | lm loss: 2.075566E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.688 | TFLOPs: 20.01 | +31: iteration 32710/ 39672 | consumed samples: 8373760 | consumed tokens: 17149460480 | elapsed time per iteration (s): 0.76 | learning rate: 3.360E-05 | global batch size: 256 | lm loss: 2.083216E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.344 | TFLOPs: 20.47 | +31: iteration 32720/ 39672 | consumed samples: 8376320 | consumed tokens: 17154703360 | elapsed time per iteration (s): 0.73 | learning rate: 3.356E-05 | global batch size: 256 | lm loss: 2.064087E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.180 | TFLOPs: 21.12 | +31: iteration 32730/ 39672 | consumed samples: 8378880 | consumed tokens: 17159946240 | elapsed time per iteration (s): 0.72 | learning rate: 3.353E-05 | global batch size: 256 | lm loss: 2.089228E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.888 | TFLOPs: 21.65 | +31: iteration 32740/ 39672 | consumed samples: 8381440 | consumed tokens: 17165189120 | elapsed time per iteration (s): 0.76 | learning rate: 3.349E-05 | global batch size: 256 | lm loss: 2.070878E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.771 | TFLOPs: 20.43 | +31: iteration 32750/ 39672 | consumed samples: 8384000 | consumed tokens: 17170432000 | elapsed time per iteration (s): 0.79 | learning rate: 3.345E-05 | global batch size: 256 | lm loss: 2.095852E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.332 | TFLOPs: 19.68 | +31: iteration 32760/ 39672 | consumed samples: 8386560 | consumed tokens: 17175674880 | elapsed time per iteration (s): 0.76 | learning rate: 3.341E-05 | global batch size: 256 | lm loss: 2.084301E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.106 | TFLOPs: 20.27 | +31: iteration 32770/ 39672 | consumed samples: 8389120 | consumed tokens: 17180917760 | elapsed time per iteration (s): 0.72 | learning rate: 3.337E-05 | global batch size: 256 | lm loss: 2.094119E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.761 | TFLOPs: 21.58 | +31: iteration 32780/ 39672 | consumed samples: 8391680 | consumed tokens: 17186160640 | elapsed time per iteration (s): 0.79 | learning rate: 3.334E-05 | global batch size: 256 | lm loss: 2.067763E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.412 | TFLOPs: 19.63 | +31: iteration 32790/ 39672 | consumed samples: 8394240 | consumed tokens: 17191403520 | elapsed time per iteration (s): 0.76 | learning rate: 3.330E-05 | global batch size: 256 | lm loss: 2.090078E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.715 | TFLOPs: 20.37 | +31: iteration 32800/ 39672 | consumed samples: 8396800 | consumed tokens: 17196646400 | elapsed time per iteration (s): 0.76 | learning rate: 3.326E-05 | global batch size: 256 | lm loss: 2.078332E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.572 | TFLOPs: 20.48 | +31: iteration 32810/ 39672 | consumed samples: 8399360 | consumed tokens: 17201889280 | elapsed time per iteration (s): 0.81 | learning rate: 3.322E-05 | global batch size: 256 | lm loss: 2.098578E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.555 | TFLOPs: 19.21 | +31: iteration 32820/ 39672 | consumed samples: 8401920 | consumed tokens: 17207132160 | elapsed time per iteration (s): 0.78 | learning rate: 3.319E-05 | global batch size: 256 | lm loss: 2.101928E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.042 | TFLOPs: 19.91 | +31: iteration 32830/ 39672 | consumed samples: 8404480 | consumed tokens: 17212375040 | elapsed time per iteration (s): 0.78 | learning rate: 3.315E-05 | global batch size: 256 | lm loss: 2.120116E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.554 | TFLOPs: 19.82 | +31: iteration 32840/ 39672 | consumed samples: 8407040 | consumed tokens: 17217617920 | elapsed time per iteration (s): 0.76 | learning rate: 3.311E-05 | global batch size: 256 | lm loss: 2.098623E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.354 | TFLOPs: 20.35 | +31: iteration 32850/ 39672 | consumed samples: 8409600 | consumed tokens: 17222860800 | elapsed time per iteration (s): 0.80 | learning rate: 3.307E-05 | global batch size: 256 | lm loss: 2.066221E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.463 | TFLOPs: 19.39 | +31: iteration 32860/ 39672 | consumed samples: 8412160 | consumed tokens: 17228103680 | elapsed time per iteration (s): 0.82 | learning rate: 3.304E-05 | global batch size: 256 | lm loss: 2.094341E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.712 | TFLOPs: 18.86 | +31: iteration 32870/ 39672 | consumed samples: 8414720 | consumed tokens: 17233346560 | elapsed time per iteration (s): 0.84 | learning rate: 3.300E-05 | global batch size: 256 | lm loss: 2.076118E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.236 | TFLOPs: 18.41 | +31: iteration 32880/ 39672 | consumed samples: 8417280 | consumed tokens: 17238589440 | elapsed time per iteration (s): 0.86 | learning rate: 3.296E-05 | global batch size: 256 | lm loss: 2.080309E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.999 | TFLOPs: 18.03 | +31: iteration 32890/ 39672 | consumed samples: 8419840 | consumed tokens: 17243832320 | elapsed time per iteration (s): 0.74 | learning rate: 3.292E-05 | global batch size: 256 | lm loss: 2.067028E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.858 | TFLOPs: 20.92 | +31: iteration 32900/ 39672 | consumed samples: 8422400 | consumed tokens: 17249075200 | elapsed time per iteration (s): 0.75 | learning rate: 3.289E-05 | global batch size: 256 | lm loss: 2.078060E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.422 | TFLOPs: 20.66 | +31: iteration 32910/ 39672 | consumed samples: 8424960 | consumed tokens: 17254318080 | elapsed time per iteration (s): 0.75 | learning rate: 3.285E-05 | global batch size: 256 | lm loss: 2.077187E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.121 | TFLOPs: 20.52 | +31: iteration 32920/ 39672 | consumed samples: 8427520 | consumed tokens: 17259560960 | elapsed time per iteration (s): 0.77 | learning rate: 3.281E-05 | global batch size: 256 | lm loss: 2.068752E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.456 | TFLOPs: 20.23 | +31: iteration 32930/ 39672 | consumed samples: 8430080 | consumed tokens: 17264803840 | elapsed time per iteration (s): 0.73 | learning rate: 3.278E-05 | global batch size: 256 | lm loss: 2.115445E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.214 | TFLOPs: 21.31 | +31: iteration 32940/ 39672 | consumed samples: 8432640 | consumed tokens: 17270046720 | elapsed time per iteration (s): 0.88 | learning rate: 3.274E-05 | global batch size: 256 | lm loss: 2.109888E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 290.176 | TFLOPs: 17.55 | +31: iteration 32950/ 39672 | consumed samples: 8435200 | consumed tokens: 17275289600 | elapsed time per iteration (s): 0.82 | learning rate: 3.270E-05 | global batch size: 256 | lm loss: 2.107750E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.444 | TFLOPs: 18.78 | +31: iteration 32960/ 39672 | consumed samples: 8437760 | consumed tokens: 17280532480 | elapsed time per iteration (s): 0.82 | learning rate: 3.267E-05 | global batch size: 256 | lm loss: 2.081016E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.689 | TFLOPs: 18.86 | +31: iteration 32970/ 39672 | consumed samples: 8440320 | consumed tokens: 17285775360 | elapsed time per iteration (s): 0.81 | learning rate: 3.263E-05 | global batch size: 256 | lm loss: 2.092777E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.188 | TFLOPs: 19.07 | +31: iteration 32980/ 39672 | consumed samples: 8442880 | consumed tokens: 17291018240 | elapsed time per iteration (s): 0.85 | learning rate: 3.259E-05 | global batch size: 256 | lm loss: 2.109118E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.561 | TFLOPs: 18.18 | +31: iteration 32990/ 39672 | consumed samples: 8445440 | consumed tokens: 17296261120 | elapsed time per iteration (s): 0.83 | learning rate: 3.255E-05 | global batch size: 256 | lm loss: 2.059813E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.469 | TFLOPs: 18.72 | +31: iteration 33000/ 39672 | consumed samples: 8448000 | consumed tokens: 17301504000 | elapsed time per iteration (s): 0.83 | learning rate: 3.252E-05 | global batch size: 256 | lm loss: 2.115937E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.340 | TFLOPs: 18.71 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 33000 | lm loss value: 2.050561E+00 | lm loss PPL: 7.772262E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 33010/ 39672 | consumed samples: 8450560 | consumed tokens: 17306746880 | elapsed time per iteration (s): 0.82 | learning rate: 3.248E-05 | global batch size: 256 | lm loss: 2.101824E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.950 | TFLOPs: 18.87 | +31: iteration 33020/ 39672 | consumed samples: 8453120 | consumed tokens: 17311989760 | elapsed time per iteration (s): 0.83 | learning rate: 3.245E-05 | global batch size: 256 | lm loss: 2.099052E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.004 | TFLOPs: 18.75 | +31: iteration 33030/ 39672 | consumed samples: 8455680 | consumed tokens: 17317232640 | elapsed time per iteration (s): 0.82 | learning rate: 3.241E-05 | global batch size: 256 | lm loss: 2.092348E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.084 | TFLOPs: 19.00 | +31: iteration 33040/ 39672 | consumed samples: 8458240 | consumed tokens: 17322475520 | elapsed time per iteration (s): 0.84 | learning rate: 3.237E-05 | global batch size: 256 | lm loss: 2.060700E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.923 | TFLOPs: 18.45 | +31: iteration 33050/ 39672 | consumed samples: 8460800 | consumed tokens: 17327718400 | elapsed time per iteration (s): 0.82 | learning rate: 3.234E-05 | global batch size: 256 | lm loss: 2.055315E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.890 | TFLOPs: 18.99 | +31: iteration 33060/ 39672 | consumed samples: 8463360 | consumed tokens: 17332961280 | elapsed time per iteration (s): 0.85 | learning rate: 3.230E-05 | global batch size: 256 | lm loss: 2.074534E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.942 | TFLOPs: 18.21 | +31: iteration 33070/ 39672 | consumed samples: 8465920 | consumed tokens: 17338204160 | elapsed time per iteration (s): 0.81 | learning rate: 3.226E-05 | global batch size: 256 | lm loss: 2.077184E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.625 | TFLOPs: 19.22 | +31: iteration 33080/ 39672 | consumed samples: 8468480 | consumed tokens: 17343447040 | elapsed time per iteration (s): 0.82 | learning rate: 3.223E-05 | global batch size: 256 | lm loss: 2.050613E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.209 | TFLOPs: 18.89 | +31: iteration 33090/ 39672 | consumed samples: 8471040 | consumed tokens: 17348689920 | elapsed time per iteration (s): 0.80 | learning rate: 3.219E-05 | global batch size: 256 | lm loss: 2.086761E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.374 | TFLOPs: 19.44 | +31: iteration 33100/ 39672 | consumed samples: 8473600 | consumed tokens: 17353932800 | elapsed time per iteration (s): 0.74 | learning rate: 3.215E-05 | global batch size: 256 | lm loss: 2.083699E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.915 | TFLOPs: 20.81 | +31: iteration 33110/ 39672 | consumed samples: 8476160 | consumed tokens: 17359175680 | elapsed time per iteration (s): 0.80 | learning rate: 3.212E-05 | global batch size: 256 | lm loss: 2.083138E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.666 | TFLOPs: 19.40 | +31: iteration 33120/ 39672 | consumed samples: 8478720 | consumed tokens: 17364418560 | elapsed time per iteration (s): 0.82 | learning rate: 3.208E-05 | global batch size: 256 | lm loss: 2.047955E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.351 | TFLOPs: 18.90 | +31: iteration 33130/ 39672 | consumed samples: 8481280 | consumed tokens: 17369661440 | elapsed time per iteration (s): 0.81 | learning rate: 3.205E-05 | global batch size: 256 | lm loss: 2.060993E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.364 | TFLOPs: 19.02 | +31: iteration 33140/ 39672 | consumed samples: 8483840 | consumed tokens: 17374904320 | elapsed time per iteration (s): 0.78 | learning rate: 3.201E-05 | global batch size: 256 | lm loss: 2.061088E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.577 | TFLOPs: 19.82 | +31: iteration 33150/ 39672 | consumed samples: 8486400 | consumed tokens: 17380147200 | elapsed time per iteration (s): 0.80 | learning rate: 3.197E-05 | global batch size: 256 | lm loss: 2.071564E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.889 | TFLOPs: 19.35 | +31: iteration 33160/ 39672 | consumed samples: 8488960 | consumed tokens: 17385390080 | elapsed time per iteration (s): 0.76 | learning rate: 3.194E-05 | global batch size: 256 | lm loss: 2.089810E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.506 | TFLOPs: 20.30 | +31: iteration 33170/ 39672 | consumed samples: 8491520 | consumed tokens: 17390632960 | elapsed time per iteration (s): 0.76 | learning rate: 3.190E-05 | global batch size: 256 | lm loss: 2.080895E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.147 | TFLOPs: 20.46 | +31: iteration 33180/ 39672 | consumed samples: 8494080 | consumed tokens: 17395875840 | elapsed time per iteration (s): 0.83 | learning rate: 3.187E-05 | global batch size: 256 | lm loss: 2.083600E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.831 | TFLOPs: 18.68 | +31: iteration 33190/ 39672 | consumed samples: 8496640 | consumed tokens: 17401118720 | elapsed time per iteration (s): 0.76 | learning rate: 3.183E-05 | global batch size: 256 | lm loss: 2.082031E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.841 | TFLOPs: 20.32 | +31: iteration 33200/ 39672 | consumed samples: 8499200 | consumed tokens: 17406361600 | elapsed time per iteration (s): 0.75 | learning rate: 3.180E-05 | global batch size: 256 | lm loss: 2.073251E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.109 | TFLOPs: 20.64 | +31: iteration 33210/ 39672 | consumed samples: 8501760 | consumed tokens: 17411604480 | elapsed time per iteration (s): 0.75 | learning rate: 3.176E-05 | global batch size: 256 | lm loss: 2.087004E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.722 | TFLOPs: 20.73 | +31: iteration 33220/ 39672 | consumed samples: 8504320 | consumed tokens: 17416847360 | elapsed time per iteration (s): 0.77 | learning rate: 3.172E-05 | global batch size: 256 | lm loss: 2.084145E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.900 | TFLOPs: 20.02 | +31: iteration 33230/ 39672 | consumed samples: 8506880 | consumed tokens: 17422090240 | elapsed time per iteration (s): 0.79 | learning rate: 3.169E-05 | global batch size: 256 | lm loss: 2.078524E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.647 | TFLOPs: 19.58 | +31: iteration 33240/ 39672 | consumed samples: 8509440 | consumed tokens: 17427333120 | elapsed time per iteration (s): 0.78 | learning rate: 3.165E-05 | global batch size: 256 | lm loss: 2.102138E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.419 | TFLOPs: 19.87 | +31: iteration 33250/ 39672 | consumed samples: 8512000 | consumed tokens: 17432576000 | elapsed time per iteration (s): 0.83 | learning rate: 3.162E-05 | global batch size: 256 | lm loss: 2.083109E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.987 | TFLOPs: 18.75 | +31: iteration 33260/ 39672 | consumed samples: 8514560 | consumed tokens: 17437818880 | elapsed time per iteration (s): 0.82 | learning rate: 3.158E-05 | global batch size: 256 | lm loss: 2.052179E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.938 | TFLOPs: 18.81 | +31: iteration 33270/ 39672 | consumed samples: 8517120 | consumed tokens: 17443061760 | elapsed time per iteration (s): 0.80 | learning rate: 3.155E-05 | global batch size: 256 | lm loss: 2.115365E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.868 | TFLOPs: 19.35 | +31: iteration 33280/ 39672 | consumed samples: 8519680 | consumed tokens: 17448304640 | elapsed time per iteration (s): 0.86 | learning rate: 3.151E-05 | global batch size: 256 | lm loss: 2.121870E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.141 | TFLOPs: 18.10 | +31: iteration 33290/ 39672 | consumed samples: 8522240 | consumed tokens: 17453547520 | elapsed time per iteration (s): 0.80 | learning rate: 3.148E-05 | global batch size: 256 | lm loss: 2.101732E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.124 | TFLOPs: 19.43 | +31: iteration 33300/ 39672 | consumed samples: 8524800 | consumed tokens: 17458790400 | elapsed time per iteration (s): 0.77 | learning rate: 3.144E-05 | global batch size: 256 | lm loss: 2.058036E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.785 | TFLOPs: 20.07 | +31: iteration 33310/ 39672 | consumed samples: 8527360 | consumed tokens: 17464033280 | elapsed time per iteration (s): 0.80 | learning rate: 3.141E-05 | global batch size: 256 | lm loss: 2.121012E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.086 | TFLOPs: 19.30 | +31: iteration 33320/ 39672 | consumed samples: 8529920 | consumed tokens: 17469276160 | elapsed time per iteration (s): 0.79 | learning rate: 3.137E-05 | global batch size: 256 | lm loss: 2.112182E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.601 | TFLOPs: 19.52 | +31: iteration 33330/ 39672 | consumed samples: 8532480 | consumed tokens: 17474519040 | elapsed time per iteration (s): 0.81 | learning rate: 3.134E-05 | global batch size: 256 | lm loss: 2.087379E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.366 | TFLOPs: 19.20 | +31: iteration 33340/ 39672 | consumed samples: 8535040 | consumed tokens: 17479761920 | elapsed time per iteration (s): 0.82 | learning rate: 3.130E-05 | global batch size: 256 | lm loss: 2.091800E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.899 | TFLOPs: 18.87 | +31: iteration 33350/ 39672 | consumed samples: 8537600 | consumed tokens: 17485004800 | elapsed time per iteration (s): 0.84 | learning rate: 3.127E-05 | global batch size: 256 | lm loss: 2.058384E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.015 | TFLOPs: 18.33 | +31: iteration 33360/ 39672 | consumed samples: 8540160 | consumed tokens: 17490247680 | elapsed time per iteration (s): 0.83 | learning rate: 3.123E-05 | global batch size: 256 | lm loss: 2.079792E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.186 | TFLOPs: 18.77 | +31: iteration 33370/ 39672 | consumed samples: 8542720 | consumed tokens: 17495490560 | elapsed time per iteration (s): 0.78 | learning rate: 3.120E-05 | global batch size: 256 | lm loss: 2.084172E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.571 | TFLOPs: 19.88 | +31: iteration 33380/ 39672 | consumed samples: 8545280 | consumed tokens: 17500733440 | elapsed time per iteration (s): 0.80 | learning rate: 3.116E-05 | global batch size: 256 | lm loss: 2.107297E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.052 | TFLOPs: 19.24 | +31: iteration 33390/ 39672 | consumed samples: 8547840 | consumed tokens: 17505976320 | elapsed time per iteration (s): 0.85 | learning rate: 3.113E-05 | global batch size: 256 | lm loss: 2.094003E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.399 | TFLOPs: 18.29 | +31: iteration 33400/ 39672 | consumed samples: 8550400 | consumed tokens: 17511219200 | elapsed time per iteration (s): 0.78 | learning rate: 3.109E-05 | global batch size: 256 | lm loss: 2.086754E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.796 | TFLOPs: 19.95 | +31: iteration 33410/ 39672 | consumed samples: 8552960 | consumed tokens: 17516462080 | elapsed time per iteration (s): 0.77 | learning rate: 3.106E-05 | global batch size: 256 | lm loss: 2.097633E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.712 | TFLOPs: 20.01 | +31: iteration 33420/ 39672 | consumed samples: 8555520 | consumed tokens: 17521704960 | elapsed time per iteration (s): 0.84 | learning rate: 3.102E-05 | global batch size: 256 | lm loss: 2.049883E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.148 | TFLOPs: 18.46 | +31: iteration 33430/ 39672 | consumed samples: 8558080 | consumed tokens: 17526947840 | elapsed time per iteration (s): 0.83 | learning rate: 3.099E-05 | global batch size: 256 | lm loss: 2.080516E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.627 | TFLOPs: 18.73 | +31: iteration 33440/ 39672 | consumed samples: 8560640 | consumed tokens: 17532190720 | elapsed time per iteration (s): 0.83 | learning rate: 3.096E-05 | global batch size: 256 | lm loss: 2.059141E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.047 | TFLOPs: 18.64 | +31: iteration 33450/ 39672 | consumed samples: 8563200 | consumed tokens: 17537433600 | elapsed time per iteration (s): 0.81 | learning rate: 3.092E-05 | global batch size: 256 | lm loss: 2.114240E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.877 | TFLOPs: 19.05 | +31: iteration 33460/ 39672 | consumed samples: 8565760 | consumed tokens: 17542676480 | elapsed time per iteration (s): 0.80 | learning rate: 3.089E-05 | global batch size: 256 | lm loss: 2.104404E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.517 | TFLOPs: 19.33 | +31: iteration 33470/ 39672 | consumed samples: 8568320 | consumed tokens: 17547919360 | elapsed time per iteration (s): 0.79 | learning rate: 3.085E-05 | global batch size: 256 | lm loss: 2.071896E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.409 | TFLOPs: 19.69 | +31: iteration 33480/ 39672 | consumed samples: 8570880 | consumed tokens: 17553162240 | elapsed time per iteration (s): 0.81 | learning rate: 3.082E-05 | global batch size: 256 | lm loss: 2.084504E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.273 | TFLOPs: 19.13 | +31: iteration 33490/ 39672 | consumed samples: 8573440 | consumed tokens: 17558405120 | elapsed time per iteration (s): 0.86 | learning rate: 3.078E-05 | global batch size: 256 | lm loss: 2.092961E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.247 | TFLOPs: 18.10 | +31: iteration 33500/ 39672 | consumed samples: 8576000 | consumed tokens: 17563648000 | elapsed time per iteration (s): 0.80 | learning rate: 3.075E-05 | global batch size: 256 | lm loss: 2.079294E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.148 | TFLOPs: 19.37 | +31: iteration 33510/ 39672 | consumed samples: 8578560 | consumed tokens: 17568890880 | elapsed time per iteration (s): 0.84 | learning rate: 3.072E-05 | global batch size: 256 | lm loss: 2.084384E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.366 | TFLOPs: 18.41 | +31: iteration 33520/ 39672 | consumed samples: 8581120 | consumed tokens: 17574133760 | elapsed time per iteration (s): 0.80 | learning rate: 3.068E-05 | global batch size: 256 | lm loss: 2.069216E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.916 | TFLOPs: 19.29 | +31: iteration 33530/ 39672 | consumed samples: 8583680 | consumed tokens: 17579376640 | elapsed time per iteration (s): 0.81 | learning rate: 3.065E-05 | global batch size: 256 | lm loss: 2.075030E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.534 | TFLOPs: 19.09 | +31: iteration 33540/ 39672 | consumed samples: 8586240 | consumed tokens: 17584619520 | elapsed time per iteration (s): 0.83 | learning rate: 3.061E-05 | global batch size: 256 | lm loss: 2.083799E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.093 | TFLOPs: 18.70 | +31: iteration 33550/ 39672 | consumed samples: 8588800 | consumed tokens: 17589862400 | elapsed time per iteration (s): 0.83 | learning rate: 3.058E-05 | global batch size: 256 | lm loss: 2.108518E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.590 | TFLOPs: 18.67 | +31: iteration 33560/ 39672 | consumed samples: 8591360 | consumed tokens: 17595105280 | elapsed time per iteration (s): 0.80 | learning rate: 3.055E-05 | global batch size: 256 | lm loss: 2.067181E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.829 | TFLOPs: 19.29 | +31: iteration 33570/ 39672 | consumed samples: 8593920 | consumed tokens: 17600348160 | elapsed time per iteration (s): 0.79 | learning rate: 3.051E-05 | global batch size: 256 | lm loss: 2.092450E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.221 | TFLOPs: 19.61 | +31: iteration 33580/ 39672 | consumed samples: 8596480 | consumed tokens: 17605591040 | elapsed time per iteration (s): 0.83 | learning rate: 3.048E-05 | global batch size: 256 | lm loss: 2.083753E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.434 | TFLOPs: 18.60 | +31: iteration 33590/ 39672 | consumed samples: 8599040 | consumed tokens: 17610833920 | elapsed time per iteration (s): 0.84 | learning rate: 3.044E-05 | global batch size: 256 | lm loss: 2.090567E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.042 | TFLOPs: 18.33 | +31: iteration 33600/ 39672 | consumed samples: 8601600 | consumed tokens: 17616076800 | elapsed time per iteration (s): 0.77 | learning rate: 3.041E-05 | global batch size: 256 | lm loss: 2.072895E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.794 | TFLOPs: 20.13 | +31: iteration 33610/ 39672 | consumed samples: 8604160 | consumed tokens: 17621319680 | elapsed time per iteration (s): 0.83 | learning rate: 3.038E-05 | global batch size: 256 | lm loss: 2.091943E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.011 | TFLOPs: 18.75 | +31: iteration 33620/ 39672 | consumed samples: 8606720 | consumed tokens: 17626562560 | elapsed time per iteration (s): 0.78 | learning rate: 3.034E-05 | global batch size: 256 | lm loss: 2.071210E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.338 | TFLOPs: 19.74 | +31: iteration 33630/ 39672 | consumed samples: 8609280 | consumed tokens: 17631805440 | elapsed time per iteration (s): 0.80 | learning rate: 3.031E-05 | global batch size: 256 | lm loss: 2.069764E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.657 | TFLOPs: 19.28 | +31: iteration 33640/ 39672 | consumed samples: 8611840 | consumed tokens: 17637048320 | elapsed time per iteration (s): 0.81 | learning rate: 3.028E-05 | global batch size: 256 | lm loss: 2.096169E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.159 | TFLOPs: 19.01 | +31: iteration 33650/ 39672 | consumed samples: 8614400 | consumed tokens: 17642291200 | elapsed time per iteration (s): 0.80 | learning rate: 3.024E-05 | global batch size: 256 | lm loss: 2.090298E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.407 | TFLOPs: 19.32 | +31: iteration 33660/ 39672 | consumed samples: 8616960 | consumed tokens: 17647534080 | elapsed time per iteration (s): 0.82 | learning rate: 3.021E-05 | global batch size: 256 | lm loss: 2.085292E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.090 | TFLOPs: 18.82 | +31: iteration 33670/ 39672 | consumed samples: 8619520 | consumed tokens: 17652776960 | elapsed time per iteration (s): 0.81 | learning rate: 3.018E-05 | global batch size: 256 | lm loss: 2.066822E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.976 | TFLOPs: 19.06 | +31: iteration 33680/ 39672 | consumed samples: 8622080 | consumed tokens: 17658019840 | elapsed time per iteration (s): 0.79 | learning rate: 3.014E-05 | global batch size: 256 | lm loss: 2.077368E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.128 | TFLOPs: 19.49 | +31: iteration 33690/ 39672 | consumed samples: 8624640 | consumed tokens: 17663262720 | elapsed time per iteration (s): 0.79 | learning rate: 3.011E-05 | global batch size: 256 | lm loss: 2.072876E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.641 | TFLOPs: 19.58 | +31: iteration 33700/ 39672 | consumed samples: 8627200 | consumed tokens: 17668505600 | elapsed time per iteration (s): 0.79 | learning rate: 3.008E-05 | global batch size: 256 | lm loss: 2.101148E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.245 | TFLOPs: 19.62 | +31: iteration 33710/ 39672 | consumed samples: 8629760 | consumed tokens: 17673748480 | elapsed time per iteration (s): 0.81 | learning rate: 3.004E-05 | global batch size: 256 | lm loss: 2.116282E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.548 | TFLOPs: 19.09 | +31: iteration 33720/ 39672 | consumed samples: 8632320 | consumed tokens: 17678991360 | elapsed time per iteration (s): 0.80 | learning rate: 3.001E-05 | global batch size: 256 | lm loss: 2.077555E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.135 | TFLOPs: 19.25 | +31: iteration 33730/ 39672 | consumed samples: 8634880 | consumed tokens: 17684234240 | elapsed time per iteration (s): 0.87 | learning rate: 2.998E-05 | global batch size: 256 | lm loss: 2.102881E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 294.519 | TFLOPs: 17.82 | +31: iteration 33740/ 39672 | consumed samples: 8637440 | consumed tokens: 17689477120 | elapsed time per iteration (s): 0.78 | learning rate: 2.995E-05 | global batch size: 256 | lm loss: 2.091447E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.380 | TFLOPs: 19.87 | +31: iteration 33750/ 39672 | consumed samples: 8640000 | consumed tokens: 17694720000 | elapsed time per iteration (s): 0.81 | learning rate: 2.991E-05 | global batch size: 256 | lm loss: 2.093205E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.751 | TFLOPs: 19.10 | +31: iteration 33760/ 39672 | consumed samples: 8642560 | consumed tokens: 17699962880 | elapsed time per iteration (s): 0.77 | learning rate: 2.988E-05 | global batch size: 256 | lm loss: 2.122746E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.927 | TFLOPs: 20.20 | +31: iteration 33770/ 39672 | consumed samples: 8645120 | consumed tokens: 17705205760 | elapsed time per iteration (s): 0.81 | learning rate: 2.985E-05 | global batch size: 256 | lm loss: 2.086033E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.461 | TFLOPs: 19.08 | +31: iteration 33780/ 39672 | consumed samples: 8647680 | consumed tokens: 17710448640 | elapsed time per iteration (s): 0.79 | learning rate: 2.981E-05 | global batch size: 256 | lm loss: 2.081991E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.646 | TFLOPs: 19.52 | +31: iteration 33790/ 39672 | consumed samples: 8650240 | consumed tokens: 17715691520 | elapsed time per iteration (s): 0.85 | learning rate: 2.978E-05 | global batch size: 256 | lm loss: 2.098353E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.487 | TFLOPs: 18.24 | +31: iteration 33800/ 39672 | consumed samples: 8652800 | consumed tokens: 17720934400 | elapsed time per iteration (s): 0.82 | learning rate: 2.975E-05 | global batch size: 256 | lm loss: 2.086341E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.890 | TFLOPs: 18.93 | +31: iteration 33810/ 39672 | consumed samples: 8655360 | consumed tokens: 17726177280 | elapsed time per iteration (s): 0.81 | learning rate: 2.972E-05 | global batch size: 256 | lm loss: 2.102721E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.275 | TFLOPs: 19.13 | +31: iteration 33820/ 39672 | consumed samples: 8657920 | consumed tokens: 17731420160 | elapsed time per iteration (s): 0.80 | learning rate: 2.968E-05 | global batch size: 256 | lm loss: 2.087364E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.510 | TFLOPs: 19.33 | +31: iteration 33830/ 39672 | consumed samples: 8660480 | consumed tokens: 17736663040 | elapsed time per iteration (s): 0.83 | learning rate: 2.965E-05 | global batch size: 256 | lm loss: 2.100774E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.755 | TFLOPs: 18.74 | +31: iteration 33840/ 39672 | consumed samples: 8663040 | consumed tokens: 17741905920 | elapsed time per iteration (s): 0.84 | learning rate: 2.962E-05 | global batch size: 256 | lm loss: 2.115170E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.604 | TFLOPs: 18.49 | +31: iteration 33850/ 39672 | consumed samples: 8665600 | consumed tokens: 17747148800 | elapsed time per iteration (s): 0.78 | learning rate: 2.959E-05 | global batch size: 256 | lm loss: 2.115619E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.521 | TFLOPs: 19.94 | +31: iteration 33860/ 39672 | consumed samples: 8668160 | consumed tokens: 17752391680 | elapsed time per iteration (s): 0.77 | learning rate: 2.955E-05 | global batch size: 256 | lm loss: 2.062347E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.025 | TFLOPs: 20.03 | +31: iteration 33870/ 39672 | consumed samples: 8670720 | consumed tokens: 17757634560 | elapsed time per iteration (s): 0.79 | learning rate: 2.952E-05 | global batch size: 256 | lm loss: 2.078663E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.368 | TFLOPs: 19.56 | +31: iteration 33880/ 39672 | consumed samples: 8673280 | consumed tokens: 17762877440 | elapsed time per iteration (s): 0.81 | learning rate: 2.949E-05 | global batch size: 256 | lm loss: 2.064071E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.711 | TFLOPs: 19.10 | +31: iteration 33890/ 39672 | consumed samples: 8675840 | consumed tokens: 17768120320 | elapsed time per iteration (s): 0.83 | learning rate: 2.946E-05 | global batch size: 256 | lm loss: 2.073814E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.714 | TFLOPs: 18.74 | +31: iteration 33900/ 39672 | consumed samples: 8678400 | consumed tokens: 17773363200 | elapsed time per iteration (s): 0.80 | learning rate: 2.943E-05 | global batch size: 256 | lm loss: 2.075696E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.848 | TFLOPs: 19.29 | +31: iteration 33910/ 39672 | consumed samples: 8680960 | consumed tokens: 17778606080 | elapsed time per iteration (s): 0.80 | learning rate: 2.939E-05 | global batch size: 256 | lm loss: 2.094921E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.484 | TFLOPs: 19.27 | +31: iteration 33920/ 39672 | consumed samples: 8683520 | consumed tokens: 17783848960 | elapsed time per iteration (s): 0.86 | learning rate: 2.936E-05 | global batch size: 256 | lm loss: 2.084514E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.700 | TFLOPs: 18.07 | +31: iteration 33930/ 39672 | consumed samples: 8686080 | consumed tokens: 17789091840 | elapsed time per iteration (s): 0.80 | learning rate: 2.933E-05 | global batch size: 256 | lm loss: 2.058640E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.897 | TFLOPs: 19.29 | +31: iteration 33940/ 39672 | consumed samples: 8688640 | consumed tokens: 17794334720 | elapsed time per iteration (s): 0.83 | learning rate: 2.930E-05 | global batch size: 256 | lm loss: 2.077225E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.936 | TFLOPs: 18.75 | +31: iteration 33950/ 39672 | consumed samples: 8691200 | consumed tokens: 17799577600 | elapsed time per iteration (s): 0.79 | learning rate: 2.927E-05 | global batch size: 256 | lm loss: 2.080997E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.540 | TFLOPs: 19.69 | +31: iteration 33960/ 39672 | consumed samples: 8693760 | consumed tokens: 17804820480 | elapsed time per iteration (s): 0.82 | learning rate: 2.923E-05 | global batch size: 256 | lm loss: 2.084313E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.855 | TFLOPs: 18.81 | +31: iteration 33970/ 39672 | consumed samples: 8696320 | consumed tokens: 17810063360 | elapsed time per iteration (s): 0.83 | learning rate: 2.920E-05 | global batch size: 256 | lm loss: 2.057817E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.100 | TFLOPs: 18.58 | +31: iteration 33980/ 39672 | consumed samples: 8698880 | consumed tokens: 17815306240 | elapsed time per iteration (s): 0.84 | learning rate: 2.917E-05 | global batch size: 256 | lm loss: 2.078488E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.120 | TFLOPs: 18.46 | +31: iteration 33990/ 39672 | consumed samples: 8701440 | consumed tokens: 17820549120 | elapsed time per iteration (s): 0.82 | learning rate: 2.914E-05 | global batch size: 256 | lm loss: 2.087621E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.534 | TFLOPs: 18.91 | + 0: [2022-11-30 16:43:17,478] [INFO] [logging.py:68:log_dist] [Rank 0] step=34000, skipped=0, lr=[2.910738107944474e-05, 2.910738107944474e-05, 2.910738107944474e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 34000/ 39672 | consumed samples: 8704000 | consumed tokens: 17825792000 | elapsed time per iteration (s): 0.86 | learning rate: 2.911E-05 | global batch size: 256 | lm loss: 2.098037E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.504 | TFLOPs: 17.94 | + 0: steps: 34000 loss: 2.1391 iter time (s): 0.790 samples/sec: 324.010 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 34000 | lm loss value: 2.025186E+00 | lm loss PPL: 7.577517E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 34010/ 39672 | consumed samples: 8706560 | consumed tokens: 17831034880 | elapsed time per iteration (s): 0.79 | learning rate: 2.908E-05 | global batch size: 256 | lm loss: 2.102889E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.435 | TFLOPs: 19.57 | +31: iteration 34020/ 39672 | consumed samples: 8709120 | consumed tokens: 17836277760 | elapsed time per iteration (s): 0.80 | learning rate: 2.904E-05 | global batch size: 256 | lm loss: 2.090043E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.394 | TFLOPs: 19.44 | +31: iteration 34030/ 39672 | consumed samples: 8711680 | consumed tokens: 17841520640 | elapsed time per iteration (s): 0.82 | learning rate: 2.901E-05 | global batch size: 256 | lm loss: 2.081728E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.961 | TFLOPs: 18.99 | +31: iteration 34040/ 39672 | consumed samples: 8714240 | consumed tokens: 17846763520 | elapsed time per iteration (s): 0.81 | learning rate: 2.898E-05 | global batch size: 256 | lm loss: 2.092636E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.571 | TFLOPs: 19.09 | +31: iteration 34050/ 39672 | consumed samples: 8716800 | consumed tokens: 17852006400 | elapsed time per iteration (s): 0.81 | learning rate: 2.895E-05 | global batch size: 256 | lm loss: 2.081051E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.658 | TFLOPs: 19.10 | +31: iteration 34060/ 39672 | consumed samples: 8719360 | consumed tokens: 17857249280 | elapsed time per iteration (s): 0.82 | learning rate: 2.892E-05 | global batch size: 256 | lm loss: 2.053796E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.085 | TFLOPs: 18.82 | +31: iteration 34070/ 39672 | consumed samples: 8721920 | consumed tokens: 17862492160 | elapsed time per iteration (s): 0.78 | learning rate: 2.889E-05 | global batch size: 256 | lm loss: 2.061241E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.910 | TFLOPs: 19.84 | +31: iteration 34080/ 39672 | consumed samples: 8724480 | consumed tokens: 17867735040 | elapsed time per iteration (s): 0.80 | learning rate: 2.886E-05 | global batch size: 256 | lm loss: 2.102299E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.836 | TFLOPs: 19.29 | +31: iteration 34090/ 39672 | consumed samples: 8727040 | consumed tokens: 17872977920 | elapsed time per iteration (s): 0.85 | learning rate: 2.883E-05 | global batch size: 256 | lm loss: 2.097482E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.586 | TFLOPs: 18.31 | +31: iteration 34100/ 39672 | consumed samples: 8729600 | consumed tokens: 17878220800 | elapsed time per iteration (s): 0.86 | learning rate: 2.879E-05 | global batch size: 256 | lm loss: 2.080344E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 296.934 | TFLOPs: 17.96 | +31: iteration 34110/ 39672 | consumed samples: 8732160 | consumed tokens: 17883463680 | elapsed time per iteration (s): 0.79 | learning rate: 2.876E-05 | global batch size: 256 | lm loss: 2.067282E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.364 | TFLOPs: 19.50 | +31: iteration 34120/ 39672 | consumed samples: 8734720 | consumed tokens: 17888706560 | elapsed time per iteration (s): 0.82 | learning rate: 2.873E-05 | global batch size: 256 | lm loss: 2.083492E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.407 | TFLOPs: 18.78 | +31: iteration 34130/ 39672 | consumed samples: 8737280 | consumed tokens: 17893949440 | elapsed time per iteration (s): 0.79 | learning rate: 2.870E-05 | global batch size: 256 | lm loss: 2.104188E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.058 | TFLOPs: 19.60 | +31: iteration 34140/ 39672 | consumed samples: 8739840 | consumed tokens: 17899192320 | elapsed time per iteration (s): 0.79 | learning rate: 2.867E-05 | global batch size: 256 | lm loss: 2.053261E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.348 | TFLOPs: 19.50 | +31: iteration 34150/ 39672 | consumed samples: 8742400 | consumed tokens: 17904435200 | elapsed time per iteration (s): 0.81 | learning rate: 2.864E-05 | global batch size: 256 | lm loss: 2.077314E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.421 | TFLOPs: 19.08 | +31: iteration 34160/ 39672 | consumed samples: 8744960 | consumed tokens: 17909678080 | elapsed time per iteration (s): 0.80 | learning rate: 2.861E-05 | global batch size: 256 | lm loss: 2.072650E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.635 | TFLOPs: 19.46 | +31: iteration 34170/ 39672 | consumed samples: 8747520 | consumed tokens: 17914920960 | elapsed time per iteration (s): 0.79 | learning rate: 2.858E-05 | global batch size: 256 | lm loss: 2.082350E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.289 | TFLOPs: 19.62 | +31: iteration 34180/ 39672 | consumed samples: 8750080 | consumed tokens: 17920163840 | elapsed time per iteration (s): 0.79 | learning rate: 2.855E-05 | global batch size: 256 | lm loss: 2.112632E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.044 | TFLOPs: 19.72 | +31: iteration 34190/ 39672 | consumed samples: 8752640 | consumed tokens: 17925406720 | elapsed time per iteration (s): 0.80 | learning rate: 2.852E-05 | global batch size: 256 | lm loss: 2.092525E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.274 | TFLOPs: 19.25 | +31: iteration 34200/ 39672 | consumed samples: 8755200 | consumed tokens: 17930649600 | elapsed time per iteration (s): 0.90 | learning rate: 2.849E-05 | global batch size: 256 | lm loss: 2.055925E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 283.965 | TFLOPs: 17.18 | +31: iteration 34210/ 39672 | consumed samples: 8757760 | consumed tokens: 17935892480 | elapsed time per iteration (s): 1.06 | learning rate: 2.846E-05 | global batch size: 256 | lm loss: 2.074565E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 241.592 | TFLOPs: 14.62 | +31: iteration 34220/ 39672 | consumed samples: 8760320 | consumed tokens: 17941135360 | elapsed time per iteration (s): 1.06 | learning rate: 2.843E-05 | global batch size: 256 | lm loss: 2.084047E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 241.419 | TFLOPs: 14.61 | +31: iteration 34230/ 39672 | consumed samples: 8762880 | consumed tokens: 17946378240 | elapsed time per iteration (s): 0.97 | learning rate: 2.840E-05 | global batch size: 256 | lm loss: 2.057263E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 263.130 | TFLOPs: 15.92 | +31: iteration 34240/ 39672 | consumed samples: 8765440 | consumed tokens: 17951621120 | elapsed time per iteration (s): 0.99 | learning rate: 2.836E-05 | global batch size: 256 | lm loss: 2.063371E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 258.652 | TFLOPs: 15.65 | +31: iteration 34250/ 39672 | consumed samples: 8768000 | consumed tokens: 17956864000 | elapsed time per iteration (s): 0.99 | learning rate: 2.833E-05 | global batch size: 256 | lm loss: 2.075938E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 259.535 | TFLOPs: 15.70 | +31: iteration 34260/ 39672 | consumed samples: 8770560 | consumed tokens: 17962106880 | elapsed time per iteration (s): 0.98 | learning rate: 2.830E-05 | global batch size: 256 | lm loss: 2.080825E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 261.505 | TFLOPs: 15.82 | +31: iteration 34270/ 39672 | consumed samples: 8773120 | consumed tokens: 17967349760 | elapsed time per iteration (s): 0.87 | learning rate: 2.827E-05 | global batch size: 256 | lm loss: 2.099261E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 294.534 | TFLOPs: 17.82 | +31: iteration 34280/ 39672 | consumed samples: 8775680 | consumed tokens: 17972592640 | elapsed time per iteration (s): 0.93 | learning rate: 2.824E-05 | global batch size: 256 | lm loss: 2.090939E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 276.443 | TFLOPs: 16.72 | +31: iteration 34290/ 39672 | consumed samples: 8778240 | consumed tokens: 17977835520 | elapsed time per iteration (s): 0.75 | learning rate: 2.821E-05 | global batch size: 256 | lm loss: 2.103562E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.855 | TFLOPs: 20.62 | +31: iteration 34300/ 39672 | consumed samples: 8780800 | consumed tokens: 17983078400 | elapsed time per iteration (s): 0.74 | learning rate: 2.818E-05 | global batch size: 256 | lm loss: 2.103423E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.264 | TFLOPs: 20.89 | +31: iteration 34310/ 39672 | consumed samples: 8783360 | consumed tokens: 17988321280 | elapsed time per iteration (s): 0.75 | learning rate: 2.815E-05 | global batch size: 256 | lm loss: 2.081125E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.237 | TFLOPs: 20.52 | +31: iteration 34320/ 39672 | consumed samples: 8785920 | consumed tokens: 17993564160 | elapsed time per iteration (s): 0.76 | learning rate: 2.812E-05 | global batch size: 256 | lm loss: 2.123660E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.888 | TFLOPs: 20.26 | +31: iteration 34330/ 39672 | consumed samples: 8788480 | consumed tokens: 17998807040 | elapsed time per iteration (s): 0.76 | learning rate: 2.809E-05 | global batch size: 256 | lm loss: 2.102810E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.039 | TFLOPs: 20.27 | +31: iteration 34340/ 39672 | consumed samples: 8791040 | consumed tokens: 18004049920 | elapsed time per iteration (s): 0.76 | learning rate: 2.806E-05 | global batch size: 256 | lm loss: 2.058789E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.976 | TFLOPs: 20.51 | +31: iteration 34350/ 39672 | consumed samples: 8793600 | consumed tokens: 18009292800 | elapsed time per iteration (s): 0.74 | learning rate: 2.803E-05 | global batch size: 256 | lm loss: 2.061189E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.266 | TFLOPs: 20.95 | +31: iteration 34360/ 39672 | consumed samples: 8796160 | consumed tokens: 18014535680 | elapsed time per iteration (s): 0.79 | learning rate: 2.801E-05 | global batch size: 256 | lm loss: 2.055226E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.864 | TFLOPs: 19.53 | +31: iteration 34370/ 39672 | consumed samples: 8798720 | consumed tokens: 18019778560 | elapsed time per iteration (s): 0.81 | learning rate: 2.798E-05 | global batch size: 256 | lm loss: 2.097235E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.027 | TFLOPs: 19.06 | +31: iteration 34380/ 39672 | consumed samples: 8801280 | consumed tokens: 18025021440 | elapsed time per iteration (s): 0.93 | learning rate: 2.795E-05 | global batch size: 256 | lm loss: 2.105678E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 276.299 | TFLOPs: 16.72 | +31: iteration 34390/ 39672 | consumed samples: 8803840 | consumed tokens: 18030264320 | elapsed time per iteration (s): 0.93 | learning rate: 2.792E-05 | global batch size: 256 | lm loss: 2.057948E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 275.877 | TFLOPs: 16.69 | +31: iteration 34400/ 39672 | consumed samples: 8806400 | consumed tokens: 18035507200 | elapsed time per iteration (s): 0.95 | learning rate: 2.789E-05 | global batch size: 256 | lm loss: 2.104740E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 270.639 | TFLOPs: 16.37 | +31: iteration 34410/ 39672 | consumed samples: 8808960 | consumed tokens: 18040750080 | elapsed time per iteration (s): 0.88 | learning rate: 2.786E-05 | global batch size: 256 | lm loss: 2.098056E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 290.850 | TFLOPs: 17.60 | +31: iteration 34420/ 39672 | consumed samples: 8811520 | consumed tokens: 18045992960 | elapsed time per iteration (s): 0.99 | learning rate: 2.783E-05 | global batch size: 256 | lm loss: 2.087059E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 258.556 | TFLOPs: 15.64 | +31: iteration 34430/ 39672 | consumed samples: 8814080 | consumed tokens: 18051235840 | elapsed time per iteration (s): 9.41 | learning rate: 2.780E-05 | global batch size: 256 | lm loss: 2.099556E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 27.194 | TFLOPs: 1.65 | +31: iteration 34440/ 39672 | consumed samples: 8816640 | consumed tokens: 18056478720 | elapsed time per iteration (s): 14.17 | learning rate: 2.777E-05 | global batch size: 256 | lm loss: 2.087241E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 18.067 | TFLOPs: 1.09 | +31: iteration 34450/ 39672 | consumed samples: 8819200 | consumed tokens: 18061721600 | elapsed time per iteration (s): 11.31 | learning rate: 2.774E-05 | global batch size: 256 | lm loss: 2.092378E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 22.638 | TFLOPs: 1.37 | +31: iteration 34460/ 39672 | consumed samples: 8821760 | consumed tokens: 18066964480 | elapsed time per iteration (s): 6.09 | learning rate: 2.771E-05 | global batch size: 256 | lm loss: 2.056286E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 42.063 | TFLOPs: 2.54 | +31: iteration 34470/ 39672 | consumed samples: 8824320 | consumed tokens: 18072207360 | elapsed time per iteration (s): 1.32 | learning rate: 2.768E-05 | global batch size: 256 | lm loss: 2.056104E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 194.522 | TFLOPs: 11.77 | +31: iteration 34480/ 39672 | consumed samples: 8826880 | consumed tokens: 18077450240 | elapsed time per iteration (s): 1.41 | learning rate: 2.765E-05 | global batch size: 256 | lm loss: 2.056933E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 181.277 | TFLOPs: 10.97 | +31: iteration 34490/ 39672 | consumed samples: 8829440 | consumed tokens: 18082693120 | elapsed time per iteration (s): 1.53 | learning rate: 2.762E-05 | global batch size: 256 | lm loss: 2.077848E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 167.012 | TFLOPs: 10.10 | +31: iteration 34500/ 39672 | consumed samples: 8832000 | consumed tokens: 18087936000 | elapsed time per iteration (s): 1.23 | learning rate: 2.759E-05 | global batch size: 256 | lm loss: 2.041240E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.432 | TFLOPs: 12.55 | +31: iteration 34510/ 39672 | consumed samples: 8834560 | consumed tokens: 18093178880 | elapsed time per iteration (s): 1.33 | learning rate: 2.757E-05 | global batch size: 256 | lm loss: 2.053833E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.494 | TFLOPs: 11.65 | +31: iteration 34520/ 39672 | consumed samples: 8837120 | consumed tokens: 18098421760 | elapsed time per iteration (s): 1.35 | learning rate: 2.754E-05 | global batch size: 256 | lm loss: 2.067016E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 189.072 | TFLOPs: 11.44 | +31: iteration 34530/ 39672 | consumed samples: 8839680 | consumed tokens: 18103664640 | elapsed time per iteration (s): 1.18 | learning rate: 2.751E-05 | global batch size: 256 | lm loss: 2.085624E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.403 | TFLOPs: 13.15 | +31: iteration 34540/ 39672 | consumed samples: 8842240 | consumed tokens: 18108907520 | elapsed time per iteration (s): 1.26 | learning rate: 2.748E-05 | global batch size: 256 | lm loss: 2.062777E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.359 | TFLOPs: 12.30 | +31: iteration 34550/ 39672 | consumed samples: 8844800 | consumed tokens: 18114150400 | elapsed time per iteration (s): 1.35 | learning rate: 2.745E-05 | global batch size: 256 | lm loss: 2.096153E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 189.183 | TFLOPs: 11.45 | +31: iteration 34560/ 39672 | consumed samples: 8847360 | consumed tokens: 18119393280 | elapsed time per iteration (s): 1.44 | learning rate: 2.742E-05 | global batch size: 256 | lm loss: 2.056377E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 178.298 | TFLOPs: 10.79 | +31: iteration 34570/ 39672 | consumed samples: 8849920 | consumed tokens: 18124636160 | elapsed time per iteration (s): 1.47 | learning rate: 2.739E-05 | global batch size: 256 | lm loss: 2.079687E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 173.820 | TFLOPs: 10.52 | +31: iteration 34580/ 39672 | consumed samples: 8852480 | consumed tokens: 18129879040 | elapsed time per iteration (s): 1.51 | learning rate: 2.736E-05 | global batch size: 256 | lm loss: 2.097881E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 169.047 | TFLOPs: 10.23 | +31: iteration 34590/ 39672 | consumed samples: 8855040 | consumed tokens: 18135121920 | elapsed time per iteration (s): 1.59 | learning rate: 2.734E-05 | global batch size: 256 | lm loss: 2.048953E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 160.592 | TFLOPs: 9.72 | +31: iteration 34600/ 39672 | consumed samples: 8857600 | consumed tokens: 18140364800 | elapsed time per iteration (s): 1.45 | learning rate: 2.731E-05 | global batch size: 256 | lm loss: 2.072119E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 176.932 | TFLOPs: 10.70 | +31: iteration 34610/ 39672 | consumed samples: 8860160 | consumed tokens: 18145607680 | elapsed time per iteration (s): 1.51 | learning rate: 2.728E-05 | global batch size: 256 | lm loss: 2.029674E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 169.697 | TFLOPs: 10.27 | +31: iteration 34620/ 39672 | consumed samples: 8862720 | consumed tokens: 18150850560 | elapsed time per iteration (s): 1.39 | learning rate: 2.725E-05 | global batch size: 256 | lm loss: 2.064248E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 184.681 | TFLOPs: 11.17 | +31: iteration 34630/ 39672 | consumed samples: 8865280 | consumed tokens: 18156093440 | elapsed time per iteration (s): 1.36 | learning rate: 2.722E-05 | global batch size: 256 | lm loss: 2.070665E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 188.357 | TFLOPs: 11.40 | +31: iteration 34640/ 39672 | consumed samples: 8867840 | consumed tokens: 18161336320 | elapsed time per iteration (s): 1.42 | learning rate: 2.719E-05 | global batch size: 256 | lm loss: 2.085008E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 179.979 | TFLOPs: 10.89 | +31: iteration 34650/ 39672 | consumed samples: 8870400 | consumed tokens: 18166579200 | elapsed time per iteration (s): 1.40 | learning rate: 2.717E-05 | global batch size: 256 | lm loss: 2.086611E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 182.872 | TFLOPs: 11.06 | +31: iteration 34660/ 39672 | consumed samples: 8872960 | consumed tokens: 18171822080 | elapsed time per iteration (s): 1.16 | learning rate: 2.714E-05 | global batch size: 256 | lm loss: 2.076070E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.852 | TFLOPs: 13.30 | +31: iteration 34670/ 39672 | consumed samples: 8875520 | consumed tokens: 18177064960 | elapsed time per iteration (s): 1.39 | learning rate: 2.711E-05 | global batch size: 256 | lm loss: 2.085622E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 184.035 | TFLOPs: 11.13 | +31: iteration 34680/ 39672 | consumed samples: 8878080 | consumed tokens: 18182307840 | elapsed time per iteration (s): 1.28 | learning rate: 2.708E-05 | global batch size: 256 | lm loss: 2.079546E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.039 | TFLOPs: 12.10 | +31: iteration 34690/ 39672 | consumed samples: 8880640 | consumed tokens: 18187550720 | elapsed time per iteration (s): 1.77 | learning rate: 2.705E-05 | global batch size: 256 | lm loss: 2.080782E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 144.535 | TFLOPs: 8.74 | +31: iteration 34700/ 39672 | consumed samples: 8883200 | consumed tokens: 18192793600 | elapsed time per iteration (s): 2.09 | learning rate: 2.703E-05 | global batch size: 256 | lm loss: 2.067426E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 122.521 | TFLOPs: 7.41 | +31: iteration 34710/ 39672 | consumed samples: 8885760 | consumed tokens: 18198036480 | elapsed time per iteration (s): 1.45 | learning rate: 2.700E-05 | global batch size: 256 | lm loss: 2.079367E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 176.604 | TFLOPs: 10.68 | +31: iteration 34720/ 39672 | consumed samples: 8888320 | consumed tokens: 18203279360 | elapsed time per iteration (s): 0.93 | learning rate: 2.697E-05 | global batch size: 256 | lm loss: 2.085986E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 275.577 | TFLOPs: 16.67 | +31: iteration 34730/ 39672 | consumed samples: 8890880 | consumed tokens: 18208522240 | elapsed time per iteration (s): 0.82 | learning rate: 2.694E-05 | global batch size: 256 | lm loss: 2.094091E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.409 | TFLOPs: 18.90 | +31: iteration 34740/ 39672 | consumed samples: 8893440 | consumed tokens: 18213765120 | elapsed time per iteration (s): 1.09 | learning rate: 2.692E-05 | global batch size: 256 | lm loss: 2.086119E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 235.645 | TFLOPs: 14.26 | +31: iteration 34750/ 39672 | consumed samples: 8896000 | consumed tokens: 18219008000 | elapsed time per iteration (s): 0.82 | learning rate: 2.689E-05 | global batch size: 256 | lm loss: 2.082404E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.034 | TFLOPs: 19.00 | +31: iteration 34760/ 39672 | consumed samples: 8898560 | consumed tokens: 18224250880 | elapsed time per iteration (s): 1.02 | learning rate: 2.686E-05 | global batch size: 256 | lm loss: 2.072893E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 250.933 | TFLOPs: 15.18 | +31: iteration 34770/ 39672 | consumed samples: 8901120 | consumed tokens: 18229493760 | elapsed time per iteration (s): 0.82 | learning rate: 2.683E-05 | global batch size: 256 | lm loss: 2.061697E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.933 | TFLOPs: 18.81 | +31: iteration 34780/ 39672 | consumed samples: 8903680 | consumed tokens: 18234736640 | elapsed time per iteration (s): 1.05 | learning rate: 2.681E-05 | global batch size: 256 | lm loss: 2.045796E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 243.085 | TFLOPs: 14.71 | +31: iteration 34790/ 39672 | consumed samples: 8906240 | consumed tokens: 18239979520 | elapsed time per iteration (s): 1.28 | learning rate: 2.678E-05 | global batch size: 256 | lm loss: 2.067042E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.013 | TFLOPs: 12.10 | +31: iteration 34800/ 39672 | consumed samples: 8908800 | consumed tokens: 18245222400 | elapsed time per iteration (s): 0.87 | learning rate: 2.675E-05 | global batch size: 256 | lm loss: 2.073858E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.128 | TFLOPs: 17.85 | +31: iteration 34810/ 39672 | consumed samples: 8911360 | consumed tokens: 18250465280 | elapsed time per iteration (s): 0.86 | learning rate: 2.672E-05 | global batch size: 256 | lm loss: 2.083881E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.075 | TFLOPs: 17.97 | +31: iteration 34820/ 39672 | consumed samples: 8913920 | consumed tokens: 18255708160 | elapsed time per iteration (s): 0.83 | learning rate: 2.670E-05 | global batch size: 256 | lm loss: 2.054061E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.168 | TFLOPs: 18.58 | +31: iteration 34830/ 39672 | consumed samples: 8916480 | consumed tokens: 18260951040 | elapsed time per iteration (s): 1.42 | learning rate: 2.667E-05 | global batch size: 256 | lm loss: 2.059498E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 180.057 | TFLOPs: 10.89 | +31: iteration 34840/ 39672 | consumed samples: 8919040 | consumed tokens: 18266193920 | elapsed time per iteration (s): 1.23 | learning rate: 2.664E-05 | global batch size: 256 | lm loss: 2.081834E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.789 | TFLOPs: 12.63 | +31: iteration 34850/ 39672 | consumed samples: 8921600 | consumed tokens: 18271436800 | elapsed time per iteration (s): 1.33 | learning rate: 2.661E-05 | global batch size: 256 | lm loss: 2.093441E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.946 | TFLOPs: 11.67 | +31: iteration 34860/ 39672 | consumed samples: 8924160 | consumed tokens: 18276679680 | elapsed time per iteration (s): 4.23 | learning rate: 2.659E-05 | global batch size: 256 | lm loss: 2.075837E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 60.571 | TFLOPs: 3.66 | +31: iteration 34870/ 39672 | consumed samples: 8926720 | consumed tokens: 18281922560 | elapsed time per iteration (s): 8.75 | learning rate: 2.656E-05 | global batch size: 256 | lm loss: 2.119595E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 29.242 | TFLOPs: 1.77 | +31: iteration 34880/ 39672 | consumed samples: 8929280 | consumed tokens: 18287165440 | elapsed time per iteration (s): 8.87 | learning rate: 2.653E-05 | global batch size: 256 | lm loss: 2.055954E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 28.855 | TFLOPs: 1.75 | +31: iteration 34890/ 39672 | consumed samples: 8931840 | consumed tokens: 18292408320 | elapsed time per iteration (s): 2.64 | learning rate: 2.651E-05 | global batch size: 256 | lm loss: 2.096523E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 97.091 | TFLOPs: 5.87 | +31: iteration 34900/ 39672 | consumed samples: 8934400 | consumed tokens: 18297651200 | elapsed time per iteration (s): 1.34 | learning rate: 2.648E-05 | global batch size: 256 | lm loss: 2.092765E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 191.657 | TFLOPs: 11.59 | +31: iteration 34910/ 39672 | consumed samples: 8936960 | consumed tokens: 18302894080 | elapsed time per iteration (s): 1.39 | learning rate: 2.645E-05 | global batch size: 256 | lm loss: 2.090219E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 184.301 | TFLOPs: 11.15 | +31: iteration 34920/ 39672 | consumed samples: 8939520 | consumed tokens: 18308136960 | elapsed time per iteration (s): 1.35 | learning rate: 2.643E-05 | global batch size: 256 | lm loss: 2.063485E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 189.862 | TFLOPs: 11.49 | +31: iteration 34930/ 39672 | consumed samples: 8942080 | consumed tokens: 18313379840 | elapsed time per iteration (s): 1.26 | learning rate: 2.640E-05 | global batch size: 256 | lm loss: 2.085151E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.606 | TFLOPs: 12.26 | +31: iteration 34940/ 39672 | consumed samples: 8944640 | consumed tokens: 18318622720 | elapsed time per iteration (s): 1.12 | learning rate: 2.637E-05 | global batch size: 256 | lm loss: 2.069481E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.868 | TFLOPs: 13.79 | +31: iteration 34950/ 39672 | consumed samples: 8947200 | consumed tokens: 18323865600 | elapsed time per iteration (s): 1.26 | learning rate: 2.635E-05 | global batch size: 256 | lm loss: 2.077389E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.786 | TFLOPs: 12.33 | +31: iteration 34960/ 39672 | consumed samples: 8949760 | consumed tokens: 18329108480 | elapsed time per iteration (s): 1.24 | learning rate: 2.632E-05 | global batch size: 256 | lm loss: 2.072480E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.524 | TFLOPs: 12.49 | +31: iteration 34970/ 39672 | consumed samples: 8952320 | consumed tokens: 18334351360 | elapsed time per iteration (s): 1.27 | learning rate: 2.629E-05 | global batch size: 256 | lm loss: 2.098437E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.371 | TFLOPs: 12.24 | +31: iteration 34980/ 39672 | consumed samples: 8954880 | consumed tokens: 18339594240 | elapsed time per iteration (s): 1.40 | learning rate: 2.627E-05 | global batch size: 256 | lm loss: 2.092768E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 183.311 | TFLOPs: 11.09 | +31: iteration 34990/ 39672 | consumed samples: 8957440 | consumed tokens: 18344837120 | elapsed time per iteration (s): 1.20 | learning rate: 2.624E-05 | global batch size: 256 | lm loss: 2.113142E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.779 | TFLOPs: 12.93 | +31: iteration 35000/ 39672 | consumed samples: 8960000 | consumed tokens: 18350080000 | elapsed time per iteration (s): 1.41 | learning rate: 2.621E-05 | global batch size: 256 | lm loss: 2.105066E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 181.010 | TFLOPs: 10.95 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 35000 | lm loss value: 2.098998E+00 | lm loss PPL: 8.157988E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 35010/ 39672 | consumed samples: 8962560 | consumed tokens: 18355322880 | elapsed time per iteration (s): 1.57 | learning rate: 2.619E-05 | global batch size: 256 | lm loss: 2.090999E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 163.040 | TFLOPs: 9.86 | +31: iteration 35020/ 39672 | consumed samples: 8965120 | consumed tokens: 18360565760 | elapsed time per iteration (s): 1.46 | learning rate: 2.616E-05 | global batch size: 256 | lm loss: 2.100035E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 175.554 | TFLOPs: 10.62 | +31: iteration 35030/ 39672 | consumed samples: 8967680 | consumed tokens: 18365808640 | elapsed time per iteration (s): 1.35 | learning rate: 2.614E-05 | global batch size: 256 | lm loss: 2.093704E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 190.107 | TFLOPs: 11.50 | +31: iteration 35040/ 39672 | consumed samples: 8970240 | consumed tokens: 18371051520 | elapsed time per iteration (s): 1.25 | learning rate: 2.611E-05 | global batch size: 256 | lm loss: 2.077310E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.950 | TFLOPs: 12.40 | +31: iteration 35050/ 39672 | consumed samples: 8972800 | consumed tokens: 18376294400 | elapsed time per iteration (s): 1.19 | learning rate: 2.608E-05 | global batch size: 256 | lm loss: 2.102410E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.453 | TFLOPs: 12.97 | +31: iteration 35060/ 39672 | consumed samples: 8975360 | consumed tokens: 18381537280 | elapsed time per iteration (s): 2.66 | learning rate: 2.606E-05 | global batch size: 256 | lm loss: 2.072958E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.381 | TFLOPs: 5.83 | +31: iteration 35070/ 39672 | consumed samples: 8977920 | consumed tokens: 18386780160 | elapsed time per iteration (s): 4.00 | learning rate: 2.603E-05 | global batch size: 256 | lm loss: 2.091852E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 64.040 | TFLOPs: 3.87 | +31: iteration 35080/ 39672 | consumed samples: 8980480 | consumed tokens: 18392023040 | elapsed time per iteration (s): 8.06 | learning rate: 2.601E-05 | global batch size: 256 | lm loss: 2.053077E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 31.757 | TFLOPs: 1.92 | +31: iteration 35090/ 39672 | consumed samples: 8983040 | consumed tokens: 18397265920 | elapsed time per iteration (s): 1.97 | learning rate: 2.598E-05 | global batch size: 256 | lm loss: 2.071584E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 130.045 | TFLOPs: 7.87 | +31: iteration 35100/ 39672 | consumed samples: 8985600 | consumed tokens: 18402508800 | elapsed time per iteration (s): 1.49 | learning rate: 2.595E-05 | global batch size: 256 | lm loss: 2.051648E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 171.938 | TFLOPs: 10.40 | +31: iteration 35110/ 39672 | consumed samples: 8988160 | consumed tokens: 18407751680 | elapsed time per iteration (s): 1.57 | learning rate: 2.593E-05 | global batch size: 256 | lm loss: 2.060526E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 162.617 | TFLOPs: 9.84 | +31: iteration 35120/ 39672 | consumed samples: 8990720 | consumed tokens: 18412994560 | elapsed time per iteration (s): 1.64 | learning rate: 2.590E-05 | global batch size: 256 | lm loss: 2.072282E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 156.234 | TFLOPs: 9.45 | +31: iteration 35130/ 39672 | consumed samples: 8993280 | consumed tokens: 18418237440 | elapsed time per iteration (s): 1.60 | learning rate: 2.588E-05 | global batch size: 256 | lm loss: 2.085639E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 160.356 | TFLOPs: 9.70 | +31: iteration 35140/ 39672 | consumed samples: 8995840 | consumed tokens: 18423480320 | elapsed time per iteration (s): 3.74 | learning rate: 2.585E-05 | global batch size: 256 | lm loss: 2.083605E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 68.457 | TFLOPs: 4.14 | +31: iteration 35150/ 39672 | consumed samples: 8998400 | consumed tokens: 18428723200 | elapsed time per iteration (s): 11.93 | learning rate: 2.583E-05 | global batch size: 256 | lm loss: 2.082631E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 21.461 | TFLOPs: 1.30 | +31: iteration 35160/ 39672 | consumed samples: 9000960 | consumed tokens: 18433966080 | elapsed time per iteration (s): 11.45 | learning rate: 2.580E-05 | global batch size: 256 | lm loss: 2.068990E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 22.367 | TFLOPs: 1.35 | +31: iteration 35170/ 39672 | consumed samples: 9003520 | consumed tokens: 18439208960 | elapsed time per iteration (s): 3.86 | learning rate: 2.577E-05 | global batch size: 256 | lm loss: 2.057619E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 66.332 | TFLOPs: 4.01 | +31: iteration 35180/ 39672 | consumed samples: 9006080 | consumed tokens: 18444451840 | elapsed time per iteration (s): 1.12 | learning rate: 2.575E-05 | global batch size: 256 | lm loss: 2.071045E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.128 | TFLOPs: 13.80 | +31: iteration 35190/ 39672 | consumed samples: 9008640 | consumed tokens: 18449694720 | elapsed time per iteration (s): 1.22 | learning rate: 2.572E-05 | global batch size: 256 | lm loss: 2.087904E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.129 | TFLOPs: 12.71 | +31: iteration 35200/ 39672 | consumed samples: 9011200 | consumed tokens: 18454937600 | elapsed time per iteration (s): 1.25 | learning rate: 2.570E-05 | global batch size: 256 | lm loss: 2.090125E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.561 | TFLOPs: 12.38 | +31: iteration 35210/ 39672 | consumed samples: 9013760 | consumed tokens: 18460180480 | elapsed time per iteration (s): 1.62 | learning rate: 2.567E-05 | global batch size: 256 | lm loss: 2.079175E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 158.143 | TFLOPs: 9.57 | +31: iteration 35220/ 39672 | consumed samples: 9016320 | consumed tokens: 18465423360 | elapsed time per iteration (s): 2.11 | learning rate: 2.565E-05 | global batch size: 256 | lm loss: 2.082948E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 121.215 | TFLOPs: 7.33 | +31: iteration 35230/ 39672 | consumed samples: 9018880 | consumed tokens: 18470666240 | elapsed time per iteration (s): 1.44 | learning rate: 2.562E-05 | global batch size: 256 | lm loss: 2.080909E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 177.835 | TFLOPs: 10.76 | +31: iteration 35240/ 39672 | consumed samples: 9021440 | consumed tokens: 18475909120 | elapsed time per iteration (s): 5.26 | learning rate: 2.560E-05 | global batch size: 256 | lm loss: 2.065648E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 48.624 | TFLOPs: 2.94 | +31: iteration 35250/ 39672 | consumed samples: 9024000 | consumed tokens: 18481152000 | elapsed time per iteration (s): 4.20 | learning rate: 2.557E-05 | global batch size: 256 | lm loss: 2.078482E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 61.001 | TFLOPs: 3.69 | +31: iteration 35260/ 39672 | consumed samples: 9026560 | consumed tokens: 18486394880 | elapsed time per iteration (s): 7.73 | learning rate: 2.555E-05 | global batch size: 256 | lm loss: 2.057906E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 33.121 | TFLOPs: 2.00 | +31: iteration 35270/ 39672 | consumed samples: 9029120 | consumed tokens: 18491637760 | elapsed time per iteration (s): 8.32 | learning rate: 2.552E-05 | global batch size: 256 | lm loss: 2.067480E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 30.782 | TFLOPs: 1.86 | +31: iteration 35280/ 39672 | consumed samples: 9031680 | consumed tokens: 18496880640 | elapsed time per iteration (s): 8.65 | learning rate: 2.550E-05 | global batch size: 256 | lm loss: 2.092700E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 29.607 | TFLOPs: 1.79 | +31: iteration 35290/ 39672 | consumed samples: 9034240 | consumed tokens: 18502123520 | elapsed time per iteration (s): 1.50 | learning rate: 2.547E-05 | global batch size: 256 | lm loss: 2.054012E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 170.566 | TFLOPs: 10.32 | +31: iteration 35300/ 39672 | consumed samples: 9036800 | consumed tokens: 18507366400 | elapsed time per iteration (s): 1.54 | learning rate: 2.545E-05 | global batch size: 256 | lm loss: 2.088410E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 165.916 | TFLOPs: 10.04 | +31: iteration 35310/ 39672 | consumed samples: 9039360 | consumed tokens: 18512609280 | elapsed time per iteration (s): 1.45 | learning rate: 2.542E-05 | global batch size: 256 | lm loss: 2.065248E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 176.638 | TFLOPs: 10.69 | +31: iteration 35320/ 39672 | consumed samples: 9041920 | consumed tokens: 18517852160 | elapsed time per iteration (s): 1.37 | learning rate: 2.540E-05 | global batch size: 256 | lm loss: 2.099285E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 187.094 | TFLOPs: 11.32 | +31: iteration 35330/ 39672 | consumed samples: 9044480 | consumed tokens: 18523095040 | elapsed time per iteration (s): 2.02 | learning rate: 2.538E-05 | global batch size: 256 | lm loss: 2.051194E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 126.865 | TFLOPs: 7.68 | +31: iteration 35340/ 39672 | consumed samples: 9047040 | consumed tokens: 18528337920 | elapsed time per iteration (s): 5.11 | learning rate: 2.535E-05 | global batch size: 256 | lm loss: 2.091694E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 50.116 | TFLOPs: 3.03 | +31: iteration 35350/ 39672 | consumed samples: 9049600 | consumed tokens: 18533580800 | elapsed time per iteration (s): 3.42 | learning rate: 2.533E-05 | global batch size: 256 | lm loss: 2.072695E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 74.918 | TFLOPs: 4.53 | +31: iteration 35360/ 39672 | consumed samples: 9052160 | consumed tokens: 18538823680 | elapsed time per iteration (s): 6.43 | learning rate: 2.530E-05 | global batch size: 256 | lm loss: 2.062181E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 39.802 | TFLOPs: 2.41 | +31: iteration 35370/ 39672 | consumed samples: 9054720 | consumed tokens: 18544066560 | elapsed time per iteration (s): 11.48 | learning rate: 2.528E-05 | global batch size: 256 | lm loss: 2.061853E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 22.309 | TFLOPs: 1.35 | +31: iteration 35380/ 39672 | consumed samples: 9057280 | consumed tokens: 18549309440 | elapsed time per iteration (s): 7.67 | learning rate: 2.525E-05 | global batch size: 256 | lm loss: 2.083851E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 33.357 | TFLOPs: 2.02 | +31: iteration 35390/ 39672 | consumed samples: 9059840 | consumed tokens: 18554552320 | elapsed time per iteration (s): 5.76 | learning rate: 2.523E-05 | global batch size: 256 | lm loss: 2.094447E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 44.417 | TFLOPs: 2.69 | +31: iteration 35400/ 39672 | consumed samples: 9062400 | consumed tokens: 18559795200 | elapsed time per iteration (s): 5.39 | learning rate: 2.521E-05 | global batch size: 256 | lm loss: 2.093909E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 47.457 | TFLOPs: 2.87 | +31: iteration 35410/ 39672 | consumed samples: 9064960 | consumed tokens: 18565038080 | elapsed time per iteration (s): 2.87 | learning rate: 2.518E-05 | global batch size: 256 | lm loss: 2.057148E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.144 | TFLOPs: 5.39 | +31: iteration 35420/ 39672 | consumed samples: 9067520 | consumed tokens: 18570280960 | elapsed time per iteration (s): 1.26 | learning rate: 2.516E-05 | global batch size: 256 | lm loss: 2.086288E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.858 | TFLOPs: 12.27 | +31: iteration 35430/ 39672 | consumed samples: 9070080 | consumed tokens: 18575523840 | elapsed time per iteration (s): 1.42 | learning rate: 2.513E-05 | global batch size: 256 | lm loss: 2.070015E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 180.266 | TFLOPs: 10.91 | +31: iteration 35440/ 39672 | consumed samples: 9072640 | consumed tokens: 18580766720 | elapsed time per iteration (s): 1.61 | learning rate: 2.511E-05 | global batch size: 256 | lm loss: 2.042485E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 159.312 | TFLOPs: 9.64 | +31: iteration 35450/ 39672 | consumed samples: 9075200 | consumed tokens: 18586009600 | elapsed time per iteration (s): 1.56 | learning rate: 2.509E-05 | global batch size: 256 | lm loss: 2.046224E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 163.805 | TFLOPs: 9.91 | +31: iteration 35460/ 39672 | consumed samples: 9077760 | consumed tokens: 18591252480 | elapsed time per iteration (s): 1.40 | learning rate: 2.506E-05 | global batch size: 256 | lm loss: 2.061770E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 182.518 | TFLOPs: 11.04 | +31: iteration 35470/ 39672 | consumed samples: 9080320 | consumed tokens: 18596495360 | elapsed time per iteration (s): 1.52 | learning rate: 2.504E-05 | global batch size: 256 | lm loss: 2.080268E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 167.934 | TFLOPs: 10.16 | +31: iteration 35480/ 39672 | consumed samples: 9082880 | consumed tokens: 18601738240 | elapsed time per iteration (s): 2.13 | learning rate: 2.501E-05 | global batch size: 256 | lm loss: 2.091217E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 120.436 | TFLOPs: 7.29 | +31: iteration 35490/ 39672 | consumed samples: 9085440 | consumed tokens: 18606981120 | elapsed time per iteration (s): 1.55 | learning rate: 2.499E-05 | global batch size: 256 | lm loss: 2.101974E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 165.505 | TFLOPs: 10.01 | +31: iteration 35500/ 39672 | consumed samples: 9088000 | consumed tokens: 18612224000 | elapsed time per iteration (s): 1.66 | learning rate: 2.497E-05 | global batch size: 256 | lm loss: 2.075909E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 153.809 | TFLOPs: 9.31 | +31: iteration 35510/ 39672 | consumed samples: 9090560 | consumed tokens: 18617466880 | elapsed time per iteration (s): 1.43 | learning rate: 2.494E-05 | global batch size: 256 | lm loss: 2.076838E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 178.471 | TFLOPs: 10.80 | +31: iteration 35520/ 39672 | consumed samples: 9093120 | consumed tokens: 18622709760 | elapsed time per iteration (s): 1.32 | learning rate: 2.492E-05 | global batch size: 256 | lm loss: 2.075575E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 193.534 | TFLOPs: 11.71 | +31: iteration 35530/ 39672 | consumed samples: 9095680 | consumed tokens: 18627952640 | elapsed time per iteration (s): 1.28 | learning rate: 2.490E-05 | global batch size: 256 | lm loss: 2.069497E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.817 | TFLOPs: 12.09 | +31: iteration 35540/ 39672 | consumed samples: 9098240 | consumed tokens: 18633195520 | elapsed time per iteration (s): 1.26 | learning rate: 2.487E-05 | global batch size: 256 | lm loss: 2.061527E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.205 | TFLOPs: 12.29 | +31: iteration 35550/ 39672 | consumed samples: 9100800 | consumed tokens: 18638438400 | elapsed time per iteration (s): 1.24 | learning rate: 2.485E-05 | global batch size: 256 | lm loss: 2.091550E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.302 | TFLOPs: 12.48 | +31: iteration 35560/ 39672 | consumed samples: 9103360 | consumed tokens: 18643681280 | elapsed time per iteration (s): 1.15 | learning rate: 2.483E-05 | global batch size: 256 | lm loss: 2.088303E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.852 | TFLOPs: 13.48 | +31: iteration 35570/ 39672 | consumed samples: 9105920 | consumed tokens: 18648924160 | elapsed time per iteration (s): 1.01 | learning rate: 2.480E-05 | global batch size: 256 | lm loss: 2.102102E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 254.402 | TFLOPs: 15.39 | +31: iteration 35580/ 39672 | consumed samples: 9108480 | consumed tokens: 18654167040 | elapsed time per iteration (s): 1.17 | learning rate: 2.478E-05 | global batch size: 256 | lm loss: 2.067073E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.896 | TFLOPs: 13.24 | +31: iteration 35590/ 39672 | consumed samples: 9111040 | consumed tokens: 18659409920 | elapsed time per iteration (s): 1.10 | learning rate: 2.476E-05 | global batch size: 256 | lm loss: 2.030027E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 232.525 | TFLOPs: 14.07 | +31: iteration 35600/ 39672 | consumed samples: 9113600 | consumed tokens: 18664652800 | elapsed time per iteration (s): 1.14 | learning rate: 2.473E-05 | global batch size: 256 | lm loss: 2.085927E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.873 | TFLOPs: 13.60 | +31: iteration 35610/ 39672 | consumed samples: 9116160 | consumed tokens: 18669895680 | elapsed time per iteration (s): 1.22 | learning rate: 2.471E-05 | global batch size: 256 | lm loss: 2.080960E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.561 | TFLOPs: 12.74 | +31: iteration 35620/ 39672 | consumed samples: 9118720 | consumed tokens: 18675138560 | elapsed time per iteration (s): 1.39 | learning rate: 2.469E-05 | global batch size: 256 | lm loss: 2.068624E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 183.929 | TFLOPs: 11.13 | +31: iteration 35630/ 39672 | consumed samples: 9121280 | consumed tokens: 18680381440 | elapsed time per iteration (s): 3.70 | learning rate: 2.466E-05 | global batch size: 256 | lm loss: 2.082570E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 69.174 | TFLOPs: 4.18 | +31: iteration 35640/ 39672 | consumed samples: 9123840 | consumed tokens: 18685624320 | elapsed time per iteration (s): 3.56 | learning rate: 2.464E-05 | global batch size: 256 | lm loss: 2.069454E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 71.926 | TFLOPs: 4.35 | +31: iteration 35650/ 39672 | consumed samples: 9126400 | consumed tokens: 18690867200 | elapsed time per iteration (s): 2.35 | learning rate: 2.462E-05 | global batch size: 256 | lm loss: 2.065276E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 108.995 | TFLOPs: 6.59 | +31: iteration 35660/ 39672 | consumed samples: 9128960 | consumed tokens: 18696110080 | elapsed time per iteration (s): 0.87 | learning rate: 2.460E-05 | global batch size: 256 | lm loss: 2.089567E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.402 | TFLOPs: 17.87 | +31: iteration 35670/ 39672 | consumed samples: 9131520 | consumed tokens: 18701352960 | elapsed time per iteration (s): 1.01 | learning rate: 2.457E-05 | global batch size: 256 | lm loss: 2.073852E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 253.484 | TFLOPs: 15.34 | +31: iteration 35680/ 39672 | consumed samples: 9134080 | consumed tokens: 18706595840 | elapsed time per iteration (s): 0.79 | learning rate: 2.455E-05 | global batch size: 256 | lm loss: 2.087683E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.058 | TFLOPs: 19.73 | +31: iteration 35690/ 39672 | consumed samples: 9136640 | consumed tokens: 18711838720 | elapsed time per iteration (s): 0.81 | learning rate: 2.453E-05 | global batch size: 256 | lm loss: 2.046381E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.240 | TFLOPs: 19.13 | +31: iteration 35700/ 39672 | consumed samples: 9139200 | consumed tokens: 18717081600 | elapsed time per iteration (s): 0.80 | learning rate: 2.451E-05 | global batch size: 256 | lm loss: 2.059864E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.836 | TFLOPs: 19.35 | +31: iteration 35710/ 39672 | consumed samples: 9141760 | consumed tokens: 18722324480 | elapsed time per iteration (s): 0.93 | learning rate: 2.448E-05 | global batch size: 256 | lm loss: 2.088446E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 274.275 | TFLOPs: 16.59 | +31: iteration 35720/ 39672 | consumed samples: 9144320 | consumed tokens: 18727567360 | elapsed time per iteration (s): 0.76 | learning rate: 2.446E-05 | global batch size: 256 | lm loss: 2.043509E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.724 | TFLOPs: 20.25 | +31: iteration 35730/ 39672 | consumed samples: 9146880 | consumed tokens: 18732810240 | elapsed time per iteration (s): 0.82 | learning rate: 2.444E-05 | global batch size: 256 | lm loss: 2.096708E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.858 | TFLOPs: 18.87 | +31: iteration 35740/ 39672 | consumed samples: 9149440 | consumed tokens: 18738053120 | elapsed time per iteration (s): 0.94 | learning rate: 2.442E-05 | global batch size: 256 | lm loss: 2.085933E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 273.339 | TFLOPs: 16.54 | +31: iteration 35750/ 39672 | consumed samples: 9152000 | consumed tokens: 18743296000 | elapsed time per iteration (s): 0.75 | learning rate: 2.439E-05 | global batch size: 256 | lm loss: 2.084311E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.077 | TFLOPs: 20.63 | +31: iteration 35760/ 39672 | consumed samples: 9154560 | consumed tokens: 18748538880 | elapsed time per iteration (s): 0.73 | learning rate: 2.437E-05 | global batch size: 256 | lm loss: 2.064999E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.425 | TFLOPs: 21.14 | +31: iteration 35770/ 39672 | consumed samples: 9157120 | consumed tokens: 18753781760 | elapsed time per iteration (s): 0.73 | learning rate: 2.435E-05 | global batch size: 256 | lm loss: 2.059400E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.369 | TFLOPs: 21.14 | +31: iteration 35780/ 39672 | consumed samples: 9159680 | consumed tokens: 18759024640 | elapsed time per iteration (s): 0.71 | learning rate: 2.433E-05 | global batch size: 256 | lm loss: 2.063401E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.662 | TFLOPs: 21.76 | +31: iteration 35790/ 39672 | consumed samples: 9162240 | consumed tokens: 18764267520 | elapsed time per iteration (s): 0.82 | learning rate: 2.431E-05 | global batch size: 256 | lm loss: 2.057285E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.852 | TFLOPs: 18.93 | +31: iteration 35800/ 39672 | consumed samples: 9164800 | consumed tokens: 18769510400 | elapsed time per iteration (s): 0.76 | learning rate: 2.428E-05 | global batch size: 256 | lm loss: 2.076270E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.467 | TFLOPs: 20.29 | +31: iteration 35810/ 39672 | consumed samples: 9167360 | consumed tokens: 18774753280 | elapsed time per iteration (s): 0.81 | learning rate: 2.426E-05 | global batch size: 256 | lm loss: 2.081628E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.870 | TFLOPs: 19.23 | +31: iteration 35820/ 39672 | consumed samples: 9169920 | consumed tokens: 18779996160 | elapsed time per iteration (s): 0.78 | learning rate: 2.424E-05 | global batch size: 256 | lm loss: 2.066955E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.936 | TFLOPs: 19.78 | +31: iteration 35830/ 39672 | consumed samples: 9172480 | consumed tokens: 18785239040 | elapsed time per iteration (s): 3.93 | learning rate: 2.422E-05 | global batch size: 256 | lm loss: 2.045865E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 65.086 | TFLOPs: 3.94 | +31: iteration 35840/ 39672 | consumed samples: 9175040 | consumed tokens: 18790481920 | elapsed time per iteration (s): 4.01 | learning rate: 2.420E-05 | global batch size: 256 | lm loss: 2.048770E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 63.774 | TFLOPs: 3.86 | +31: iteration 35850/ 39672 | consumed samples: 9177600 | consumed tokens: 18795724800 | elapsed time per iteration (s): 3.57 | learning rate: 2.417E-05 | global batch size: 256 | lm loss: 2.089830E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 71.798 | TFLOPs: 4.34 | +31: iteration 35860/ 39672 | consumed samples: 9180160 | consumed tokens: 18800967680 | elapsed time per iteration (s): 1.02 | learning rate: 2.415E-05 | global batch size: 256 | lm loss: 2.069505E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 249.909 | TFLOPs: 15.12 | +31: iteration 35870/ 39672 | consumed samples: 9182720 | consumed tokens: 18806210560 | elapsed time per iteration (s): 0.79 | learning rate: 2.413E-05 | global batch size: 256 | lm loss: 2.105399E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.259 | TFLOPs: 19.50 | +31: iteration 35880/ 39672 | consumed samples: 9185280 | consumed tokens: 18811453440 | elapsed time per iteration (s): 0.81 | learning rate: 2.411E-05 | global batch size: 256 | lm loss: 2.066891E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.655 | TFLOPs: 19.04 | +31: iteration 35890/ 39672 | consumed samples: 9187840 | consumed tokens: 18816696320 | elapsed time per iteration (s): 0.78 | learning rate: 2.409E-05 | global batch size: 256 | lm loss: 2.069627E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.988 | TFLOPs: 19.84 | +31: iteration 35900/ 39672 | consumed samples: 9190400 | consumed tokens: 18821939200 | elapsed time per iteration (s): 0.80 | learning rate: 2.407E-05 | global batch size: 256 | lm loss: 2.076019E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.514 | TFLOPs: 19.45 | +31: iteration 35910/ 39672 | consumed samples: 9192960 | consumed tokens: 18827182080 | elapsed time per iteration (s): 0.78 | learning rate: 2.405E-05 | global batch size: 256 | lm loss: 2.065405E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.929 | TFLOPs: 19.90 | +31: iteration 35920/ 39672 | consumed samples: 9195520 | consumed tokens: 18832424960 | elapsed time per iteration (s): 0.82 | learning rate: 2.402E-05 | global batch size: 256 | lm loss: 2.088245E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.654 | TFLOPs: 18.91 | +31: iteration 35930/ 39672 | consumed samples: 9198080 | consumed tokens: 18837667840 | elapsed time per iteration (s): 0.74 | learning rate: 2.400E-05 | global batch size: 256 | lm loss: 2.055803E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.960 | TFLOPs: 20.87 | +31: iteration 35940/ 39672 | consumed samples: 9200640 | consumed tokens: 18842910720 | elapsed time per iteration (s): 0.75 | learning rate: 2.398E-05 | global batch size: 256 | lm loss: 2.062849E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.327 | TFLOPs: 20.59 | +31: iteration 35950/ 39672 | consumed samples: 9203200 | consumed tokens: 18848153600 | elapsed time per iteration (s): 0.78 | learning rate: 2.396E-05 | global batch size: 256 | lm loss: 2.087348E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.238 | TFLOPs: 19.98 | +31: iteration 35960/ 39672 | consumed samples: 9205760 | consumed tokens: 18853396480 | elapsed time per iteration (s): 0.81 | learning rate: 2.394E-05 | global batch size: 256 | lm loss: 2.095540E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.952 | TFLOPs: 19.05 | +31: iteration 35970/ 39672 | consumed samples: 9208320 | consumed tokens: 18858639360 | elapsed time per iteration (s): 0.82 | learning rate: 2.392E-05 | global batch size: 256 | lm loss: 2.080332E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.541 | TFLOPs: 18.97 | +31: iteration 35980/ 39672 | consumed samples: 9210880 | consumed tokens: 18863882240 | elapsed time per iteration (s): 0.83 | learning rate: 2.390E-05 | global batch size: 256 | lm loss: 2.056783E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.398 | TFLOPs: 18.66 | +31: iteration 35990/ 39672 | consumed samples: 9213440 | consumed tokens: 18869125120 | elapsed time per iteration (s): 0.82 | learning rate: 2.388E-05 | global batch size: 256 | lm loss: 2.057812E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.773 | TFLOPs: 18.80 | + 0: [2022-11-30 17:50:07,441] [INFO] [logging.py:68:log_dist] [Rank 0] step=36000, skipped=0, lr=[2.38559909342912e-05, 2.38559909342912e-05, 2.38559909342912e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 36000/ 39672 | consumed samples: 9216000 | consumed tokens: 18874368000 | elapsed time per iteration (s): 0.82 | learning rate: 2.386E-05 | global batch size: 256 | lm loss: 2.089683E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.627 | TFLOPs: 18.79 | + 0: steps: 36000 loss: 2.1259 iter time (s): 1.996 samples/sec: 128.229 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 36000 | lm loss value: 2.034726E+00 | lm loss PPL: 7.650155E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 36010/ 39672 | consumed samples: 9218560 | consumed tokens: 18879610880 | elapsed time per iteration (s): 0.84 | learning rate: 2.384E-05 | global batch size: 256 | lm loss: 2.060863E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.377 | TFLOPs: 18.41 | +31: iteration 36020/ 39672 | consumed samples: 9221120 | consumed tokens: 18884853760 | elapsed time per iteration (s): 2.92 | learning rate: 2.381E-05 | global batch size: 256 | lm loss: 2.070492E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.714 | TFLOPs: 5.31 | +31: iteration 36030/ 39672 | consumed samples: 9223680 | consumed tokens: 18890096640 | elapsed time per iteration (s): 3.85 | learning rate: 2.379E-05 | global batch size: 256 | lm loss: 2.054859E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 66.460 | TFLOPs: 4.02 | +31: iteration 36040/ 39672 | consumed samples: 9226240 | consumed tokens: 18895339520 | elapsed time per iteration (s): 2.48 | learning rate: 2.377E-05 | global batch size: 256 | lm loss: 2.065759E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 103.087 | TFLOPs: 6.24 | +31: iteration 36050/ 39672 | consumed samples: 9228800 | consumed tokens: 18900582400 | elapsed time per iteration (s): 0.90 | learning rate: 2.375E-05 | global batch size: 256 | lm loss: 2.086127E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 285.274 | TFLOPs: 17.26 | +31: iteration 36060/ 39672 | consumed samples: 9231360 | consumed tokens: 18905825280 | elapsed time per iteration (s): 0.98 | learning rate: 2.373E-05 | global batch size: 256 | lm loss: 2.092204E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 261.055 | TFLOPs: 15.79 | +31: iteration 36070/ 39672 | consumed samples: 9233920 | consumed tokens: 18911068160 | elapsed time per iteration (s): 1.00 | learning rate: 2.371E-05 | global batch size: 256 | lm loss: 2.079143E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 256.728 | TFLOPs: 15.53 | +31: iteration 36080/ 39672 | consumed samples: 9236480 | consumed tokens: 18916311040 | elapsed time per iteration (s): 0.96 | learning rate: 2.369E-05 | global batch size: 256 | lm loss: 2.063961E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 267.806 | TFLOPs: 16.20 | +31: iteration 36090/ 39672 | consumed samples: 9239040 | consumed tokens: 18921553920 | elapsed time per iteration (s): 0.74 | learning rate: 2.367E-05 | global batch size: 256 | lm loss: 2.061041E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.063 | TFLOPs: 20.88 | +31: iteration 36100/ 39672 | consumed samples: 9241600 | consumed tokens: 18926796800 | elapsed time per iteration (s): 0.75 | learning rate: 2.365E-05 | global batch size: 256 | lm loss: 2.099844E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.976 | TFLOPs: 20.69 | +31: iteration 36110/ 39672 | consumed samples: 9244160 | consumed tokens: 18932039680 | elapsed time per iteration (s): 0.82 | learning rate: 2.363E-05 | global batch size: 256 | lm loss: 2.081338E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.220 | TFLOPs: 18.89 | +31: iteration 36120/ 39672 | consumed samples: 9246720 | consumed tokens: 18937282560 | elapsed time per iteration (s): 0.77 | learning rate: 2.361E-05 | global batch size: 256 | lm loss: 2.068111E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.222 | TFLOPs: 20.22 | +31: iteration 36130/ 39672 | consumed samples: 9249280 | consumed tokens: 18942525440 | elapsed time per iteration (s): 0.75 | learning rate: 2.359E-05 | global batch size: 256 | lm loss: 2.049601E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.726 | TFLOPs: 20.67 | +31: iteration 36140/ 39672 | consumed samples: 9251840 | consumed tokens: 18947768320 | elapsed time per iteration (s): 0.78 | learning rate: 2.357E-05 | global batch size: 256 | lm loss: 2.056510E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.305 | TFLOPs: 19.74 | +31: iteration 36150/ 39672 | consumed samples: 9254400 | consumed tokens: 18953011200 | elapsed time per iteration (s): 0.81 | learning rate: 2.355E-05 | global batch size: 256 | lm loss: 2.107647E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.918 | TFLOPs: 19.23 | +31: iteration 36160/ 39672 | consumed samples: 9256960 | consumed tokens: 18958254080 | elapsed time per iteration (s): 0.71 | learning rate: 2.353E-05 | global batch size: 256 | lm loss: 2.096104E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 358.119 | TFLOPs: 21.67 | +31: iteration 36170/ 39672 | consumed samples: 9259520 | consumed tokens: 18963496960 | elapsed time per iteration (s): 0.81 | learning rate: 2.351E-05 | global batch size: 256 | lm loss: 2.088718E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 315.192 | TFLOPs: 19.07 | +31: iteration 36180/ 39672 | consumed samples: 9262080 | consumed tokens: 18968739840 | elapsed time per iteration (s): 0.77 | learning rate: 2.349E-05 | global batch size: 256 | lm loss: 2.074650E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.620 | TFLOPs: 20.18 | +31: iteration 36190/ 39672 | consumed samples: 9264640 | consumed tokens: 18973982720 | elapsed time per iteration (s): 0.87 | learning rate: 2.347E-05 | global batch size: 256 | lm loss: 2.076322E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 292.584 | TFLOPs: 17.70 | +31: iteration 36200/ 39672 | consumed samples: 9267200 | consumed tokens: 18979225600 | elapsed time per iteration (s): 0.86 | learning rate: 2.345E-05 | global batch size: 256 | lm loss: 2.087272E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 298.669 | TFLOPs: 18.07 | +31: iteration 36210/ 39672 | consumed samples: 9269760 | consumed tokens: 18984468480 | elapsed time per iteration (s): 0.73 | learning rate: 2.343E-05 | global batch size: 256 | lm loss: 2.061613E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.062 | TFLOPs: 21.12 | +31: iteration 36220/ 39672 | consumed samples: 9272320 | consumed tokens: 18989711360 | elapsed time per iteration (s): 0.84 | learning rate: 2.341E-05 | global batch size: 256 | lm loss: 2.098548E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 305.103 | TFLOPs: 18.46 | +31: iteration 36230/ 39672 | consumed samples: 9274880 | consumed tokens: 18994954240 | elapsed time per iteration (s): 0.94 | learning rate: 2.339E-05 | global batch size: 256 | lm loss: 2.088006E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 273.453 | TFLOPs: 16.54 | +31: iteration 36240/ 39672 | consumed samples: 9277440 | consumed tokens: 19000197120 | elapsed time per iteration (s): 0.97 | learning rate: 2.337E-05 | global batch size: 256 | lm loss: 2.089858E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 263.194 | TFLOPs: 15.92 | +31: iteration 36250/ 39672 | consumed samples: 9280000 | consumed tokens: 19005440000 | elapsed time per iteration (s): 1.06 | learning rate: 2.335E-05 | global batch size: 256 | lm loss: 2.062133E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 240.812 | TFLOPs: 14.57 | +31: iteration 36260/ 39672 | consumed samples: 9282560 | consumed tokens: 19010682880 | elapsed time per iteration (s): 1.03 | learning rate: 2.333E-05 | global batch size: 256 | lm loss: 2.052950E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 248.548 | TFLOPs: 15.04 | +31: iteration 36270/ 39672 | consumed samples: 9285120 | consumed tokens: 19015925760 | elapsed time per iteration (s): 0.98 | learning rate: 2.331E-05 | global batch size: 256 | lm loss: 2.089359E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 262.237 | TFLOPs: 15.86 | +31: iteration 36280/ 39672 | consumed samples: 9287680 | consumed tokens: 19021168640 | elapsed time per iteration (s): 0.82 | learning rate: 2.329E-05 | global batch size: 256 | lm loss: 2.066076E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.363 | TFLOPs: 18.84 | +31: iteration 36290/ 39672 | consumed samples: 9290240 | consumed tokens: 19026411520 | elapsed time per iteration (s): 0.74 | learning rate: 2.327E-05 | global batch size: 256 | lm loss: 2.093150E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.044 | TFLOPs: 20.81 | +31: iteration 36300/ 39672 | consumed samples: 9292800 | consumed tokens: 19031654400 | elapsed time per iteration (s): 0.83 | learning rate: 2.326E-05 | global batch size: 256 | lm loss: 2.087635E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.306 | TFLOPs: 18.59 | +31: iteration 36310/ 39672 | consumed samples: 9295360 | consumed tokens: 19036897280 | elapsed time per iteration (s): 1.02 | learning rate: 2.324E-05 | global batch size: 256 | lm loss: 2.083324E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 250.909 | TFLOPs: 15.18 | +31: iteration 36320/ 39672 | consumed samples: 9297920 | consumed tokens: 19042140160 | elapsed time per iteration (s): 0.91 | learning rate: 2.322E-05 | global batch size: 256 | lm loss: 2.063754E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 281.567 | TFLOPs: 17.03 | +31: iteration 36330/ 39672 | consumed samples: 9300480 | consumed tokens: 19047383040 | elapsed time per iteration (s): 1.13 | learning rate: 2.320E-05 | global batch size: 256 | lm loss: 2.048062E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.754 | TFLOPs: 13.66 | +31: iteration 36340/ 39672 | consumed samples: 9303040 | consumed tokens: 19052625920 | elapsed time per iteration (s): 1.07 | learning rate: 2.318E-05 | global batch size: 256 | lm loss: 2.078445E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 239.376 | TFLOPs: 14.48 | +31: iteration 36350/ 39672 | consumed samples: 9305600 | consumed tokens: 19057868800 | elapsed time per iteration (s): 1.06 | learning rate: 2.316E-05 | global batch size: 256 | lm loss: 2.048268E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 240.655 | TFLOPs: 14.56 | +31: iteration 36360/ 39672 | consumed samples: 9308160 | consumed tokens: 19063111680 | elapsed time per iteration (s): 1.00 | learning rate: 2.314E-05 | global batch size: 256 | lm loss: 2.085471E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 255.645 | TFLOPs: 15.47 | +31: iteration 36370/ 39672 | consumed samples: 9310720 | consumed tokens: 19068354560 | elapsed time per iteration (s): 0.93 | learning rate: 2.312E-05 | global batch size: 256 | lm loss: 2.075186E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 274.841 | TFLOPs: 16.63 | +31: iteration 36380/ 39672 | consumed samples: 9313280 | consumed tokens: 19073597440 | elapsed time per iteration (s): 1.00 | learning rate: 2.310E-05 | global batch size: 256 | lm loss: 2.085244E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 256.663 | TFLOPs: 15.53 | +31: iteration 36390/ 39672 | consumed samples: 9315840 | consumed tokens: 19078840320 | elapsed time per iteration (s): 0.83 | learning rate: 2.309E-05 | global batch size: 256 | lm loss: 2.068340E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.183 | TFLOPs: 18.77 | +31: iteration 36400/ 39672 | consumed samples: 9318400 | consumed tokens: 19084083200 | elapsed time per iteration (s): 0.75 | learning rate: 2.307E-05 | global batch size: 256 | lm loss: 2.089171E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.280 | TFLOPs: 20.65 | +31: iteration 36410/ 39672 | consumed samples: 9320960 | consumed tokens: 19089326080 | elapsed time per iteration (s): 1.01 | learning rate: 2.305E-05 | global batch size: 256 | lm loss: 2.058249E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 254.667 | TFLOPs: 15.41 | +31: iteration 36420/ 39672 | consumed samples: 9323520 | consumed tokens: 19094568960 | elapsed time per iteration (s): 1.05 | learning rate: 2.303E-05 | global batch size: 256 | lm loss: 2.061878E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 244.340 | TFLOPs: 14.78 | +31: iteration 36430/ 39672 | consumed samples: 9326080 | consumed tokens: 19099811840 | elapsed time per iteration (s): 0.95 | learning rate: 2.301E-05 | global batch size: 256 | lm loss: 2.074116E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 268.369 | TFLOPs: 16.24 | +31: iteration 36440/ 39672 | consumed samples: 9328640 | consumed tokens: 19105054720 | elapsed time per iteration (s): 1.12 | learning rate: 2.299E-05 | global batch size: 256 | lm loss: 2.058510E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.290 | TFLOPs: 13.87 | +31: iteration 36450/ 39672 | consumed samples: 9331200 | consumed tokens: 19110297600 | elapsed time per iteration (s): 2.88 | learning rate: 2.297E-05 | global batch size: 256 | lm loss: 2.089330E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.853 | TFLOPs: 5.38 | +31: iteration 36460/ 39672 | consumed samples: 9333760 | consumed tokens: 19115540480 | elapsed time per iteration (s): 4.96 | learning rate: 2.296E-05 | global batch size: 256 | lm loss: 2.070466E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 51.572 | TFLOPs: 3.12 | +31: iteration 36470/ 39672 | consumed samples: 9336320 | consumed tokens: 19120783360 | elapsed time per iteration (s): 2.80 | learning rate: 2.294E-05 | global batch size: 256 | lm loss: 2.059740E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 91.349 | TFLOPs: 5.53 | +31: iteration 36480/ 39672 | consumed samples: 9338880 | consumed tokens: 19126026240 | elapsed time per iteration (s): 1.51 | learning rate: 2.292E-05 | global batch size: 256 | lm loss: 2.079086E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 169.442 | TFLOPs: 10.25 | +31: iteration 36490/ 39672 | consumed samples: 9341440 | consumed tokens: 19131269120 | elapsed time per iteration (s): 1.47 | learning rate: 2.290E-05 | global batch size: 256 | lm loss: 2.092186E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 174.675 | TFLOPs: 10.57 | +31: iteration 36500/ 39672 | consumed samples: 9344000 | consumed tokens: 19136512000 | elapsed time per iteration (s): 6.15 | learning rate: 2.288E-05 | global batch size: 256 | lm loss: 2.049572E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 41.605 | TFLOPs: 2.52 | +31: iteration 36510/ 39672 | consumed samples: 9346560 | consumed tokens: 19141754880 | elapsed time per iteration (s): 6.18 | learning rate: 2.286E-05 | global batch size: 256 | lm loss: 2.081226E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 41.416 | TFLOPs: 2.51 | +31: iteration 36520/ 39672 | consumed samples: 9349120 | consumed tokens: 19146997760 | elapsed time per iteration (s): 1.64 | learning rate: 2.285E-05 | global batch size: 256 | lm loss: 2.045586E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 155.870 | TFLOPs: 9.43 | +31: iteration 36530/ 39672 | consumed samples: 9351680 | consumed tokens: 19152240640 | elapsed time per iteration (s): 1.10 | learning rate: 2.283E-05 | global batch size: 256 | lm loss: 2.077105E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 233.401 | TFLOPs: 14.12 | +31: iteration 36540/ 39672 | consumed samples: 9354240 | consumed tokens: 19157483520 | elapsed time per iteration (s): 1.08 | learning rate: 2.281E-05 | global batch size: 256 | lm loss: 2.074943E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 238.079 | TFLOPs: 14.40 | +31: iteration 36550/ 39672 | consumed samples: 9356800 | consumed tokens: 19162726400 | elapsed time per iteration (s): 0.89 | learning rate: 2.279E-05 | global batch size: 256 | lm loss: 2.068987E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 288.532 | TFLOPs: 17.46 | +31: iteration 36560/ 39672 | consumed samples: 9359360 | consumed tokens: 19167969280 | elapsed time per iteration (s): 4.09 | learning rate: 2.278E-05 | global batch size: 256 | lm loss: 2.084848E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 62.569 | TFLOPs: 3.79 | +31: iteration 36570/ 39672 | consumed samples: 9361920 | consumed tokens: 19173212160 | elapsed time per iteration (s): 3.30 | learning rate: 2.276E-05 | global batch size: 256 | lm loss: 2.056956E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 77.527 | TFLOPs: 4.69 | +31: iteration 36580/ 39672 | consumed samples: 9364480 | consumed tokens: 19178455040 | elapsed time per iteration (s): 6.59 | learning rate: 2.274E-05 | global batch size: 256 | lm loss: 2.049570E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 38.822 | TFLOPs: 2.35 | +31: iteration 36590/ 39672 | consumed samples: 9367040 | consumed tokens: 19183697920 | elapsed time per iteration (s): 2.39 | learning rate: 2.272E-05 | global batch size: 256 | lm loss: 2.059181E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 107.314 | TFLOPs: 6.49 | +31: iteration 36600/ 39672 | consumed samples: 9369600 | consumed tokens: 19188940800 | elapsed time per iteration (s): 1.05 | learning rate: 2.270E-05 | global batch size: 256 | lm loss: 2.033072E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 242.686 | TFLOPs: 14.68 | +31: iteration 36610/ 39672 | consumed samples: 9372160 | consumed tokens: 19194183680 | elapsed time per iteration (s): 1.17 | learning rate: 2.269E-05 | global batch size: 256 | lm loss: 2.103100E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.401 | TFLOPs: 13.21 | +31: iteration 36620/ 39672 | consumed samples: 9374720 | consumed tokens: 19199426560 | elapsed time per iteration (s): 1.04 | learning rate: 2.267E-05 | global batch size: 256 | lm loss: 2.074755E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 246.415 | TFLOPs: 14.91 | +31: iteration 36630/ 39672 | consumed samples: 9377280 | consumed tokens: 19204669440 | elapsed time per iteration (s): 0.92 | learning rate: 2.265E-05 | global batch size: 256 | lm loss: 2.027817E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 278.028 | TFLOPs: 16.82 | +31: iteration 36640/ 39672 | consumed samples: 9379840 | consumed tokens: 19209912320 | elapsed time per iteration (s): 1.10 | learning rate: 2.264E-05 | global batch size: 256 | lm loss: 2.075993E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 231.704 | TFLOPs: 14.02 | +31: iteration 36650/ 39672 | consumed samples: 9382400 | consumed tokens: 19215155200 | elapsed time per iteration (s): 1.24 | learning rate: 2.262E-05 | global batch size: 256 | lm loss: 2.053109E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.386 | TFLOPs: 12.49 | +31: iteration 36660/ 39672 | consumed samples: 9384960 | consumed tokens: 19220398080 | elapsed time per iteration (s): 1.34 | learning rate: 2.260E-05 | global batch size: 256 | lm loss: 2.070399E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 191.067 | TFLOPs: 11.56 | +31: iteration 36670/ 39672 | consumed samples: 9387520 | consumed tokens: 19225640960 | elapsed time per iteration (s): 1.32 | learning rate: 2.258E-05 | global batch size: 256 | lm loss: 2.086297E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 194.165 | TFLOPs: 11.75 | +31: iteration 36680/ 39672 | consumed samples: 9390080 | consumed tokens: 19230883840 | elapsed time per iteration (s): 1.27 | learning rate: 2.257E-05 | global batch size: 256 | lm loss: 2.073591E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.875 | TFLOPs: 12.21 | +31: iteration 36690/ 39672 | consumed samples: 9392640 | consumed tokens: 19236126720 | elapsed time per iteration (s): 1.23 | learning rate: 2.255E-05 | global batch size: 256 | lm loss: 2.068617E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.572 | TFLOPs: 12.62 | +31: iteration 36700/ 39672 | consumed samples: 9395200 | consumed tokens: 19241369600 | elapsed time per iteration (s): 1.24 | learning rate: 2.253E-05 | global batch size: 256 | lm loss: 2.067786E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.394 | TFLOPs: 12.49 | +31: iteration 36710/ 39672 | consumed samples: 9397760 | consumed tokens: 19246612480 | elapsed time per iteration (s): 1.28 | learning rate: 2.252E-05 | global batch size: 256 | lm loss: 2.058822E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.096 | TFLOPs: 12.11 | +31: iteration 36720/ 39672 | consumed samples: 9400320 | consumed tokens: 19251855360 | elapsed time per iteration (s): 1.14 | learning rate: 2.250E-05 | global batch size: 256 | lm loss: 2.057922E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.966 | TFLOPs: 13.55 | +31: iteration 36730/ 39672 | consumed samples: 9402880 | consumed tokens: 19257098240 | elapsed time per iteration (s): 1.10 | learning rate: 2.248E-05 | global batch size: 256 | lm loss: 2.077183E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 232.531 | TFLOPs: 14.07 | +31: iteration 36740/ 39672 | consumed samples: 9405440 | consumed tokens: 19262341120 | elapsed time per iteration (s): 0.89 | learning rate: 2.247E-05 | global batch size: 256 | lm loss: 2.089618E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 286.503 | TFLOPs: 17.33 | +31: iteration 36750/ 39672 | consumed samples: 9408000 | consumed tokens: 19267584000 | elapsed time per iteration (s): 0.75 | learning rate: 2.245E-05 | global batch size: 256 | lm loss: 2.061593E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.698 | TFLOPs: 20.61 | +31: iteration 36760/ 39672 | consumed samples: 9410560 | consumed tokens: 19272826880 | elapsed time per iteration (s): 0.80 | learning rate: 2.243E-05 | global batch size: 256 | lm loss: 2.072070E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.464 | TFLOPs: 19.39 | +31: iteration 36770/ 39672 | consumed samples: 9413120 | consumed tokens: 19278069760 | elapsed time per iteration (s): 0.82 | learning rate: 2.242E-05 | global batch size: 256 | lm loss: 2.063277E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.248 | TFLOPs: 18.95 | +31: iteration 36780/ 39672 | consumed samples: 9415680 | consumed tokens: 19283312640 | elapsed time per iteration (s): 1.04 | learning rate: 2.240E-05 | global batch size: 256 | lm loss: 2.094934E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 247.183 | TFLOPs: 14.95 | +31: iteration 36790/ 39672 | consumed samples: 9418240 | consumed tokens: 19288555520 | elapsed time per iteration (s): 0.77 | learning rate: 2.238E-05 | global batch size: 256 | lm loss: 2.080803E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.784 | TFLOPs: 20.13 | +31: iteration 36800/ 39672 | consumed samples: 9420800 | consumed tokens: 19293798400 | elapsed time per iteration (s): 0.80 | learning rate: 2.237E-05 | global batch size: 256 | lm loss: 2.056332E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.967 | TFLOPs: 19.42 | +31: iteration 36810/ 39672 | consumed samples: 9423360 | consumed tokens: 19299041280 | elapsed time per iteration (s): 1.03 | learning rate: 2.235E-05 | global batch size: 256 | lm loss: 2.074229E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 249.528 | TFLOPs: 15.10 | +31: iteration 36820/ 39672 | consumed samples: 9425920 | consumed tokens: 19304284160 | elapsed time per iteration (s): 0.91 | learning rate: 2.233E-05 | global batch size: 256 | lm loss: 2.079780E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 280.377 | TFLOPs: 16.96 | +31: iteration 36830/ 39672 | consumed samples: 9428480 | consumed tokens: 19309527040 | elapsed time per iteration (s): 0.89 | learning rate: 2.232E-05 | global batch size: 256 | lm loss: 2.081917E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 286.173 | TFLOPs: 17.31 | +31: iteration 36840/ 39672 | consumed samples: 9431040 | consumed tokens: 19314769920 | elapsed time per iteration (s): 3.81 | learning rate: 2.230E-05 | global batch size: 256 | lm loss: 2.057570E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 67.277 | TFLOPs: 4.07 | +31: iteration 36850/ 39672 | consumed samples: 9433600 | consumed tokens: 19320012800 | elapsed time per iteration (s): 3.60 | learning rate: 2.228E-05 | global batch size: 256 | lm loss: 2.092652E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 71.176 | TFLOPs: 4.31 | +31: iteration 36860/ 39672 | consumed samples: 9436160 | consumed tokens: 19325255680 | elapsed time per iteration (s): 2.97 | learning rate: 2.227E-05 | global batch size: 256 | lm loss: 2.080857E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.072 | TFLOPs: 5.21 | +31: iteration 36870/ 39672 | consumed samples: 9438720 | consumed tokens: 19330498560 | elapsed time per iteration (s): 0.89 | learning rate: 2.225E-05 | global batch size: 256 | lm loss: 2.048509E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 287.857 | TFLOPs: 17.41 | +31: iteration 36880/ 39672 | consumed samples: 9441280 | consumed tokens: 19335741440 | elapsed time per iteration (s): 0.82 | learning rate: 2.224E-05 | global batch size: 256 | lm loss: 2.040615E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.495 | TFLOPs: 18.97 | +31: iteration 36890/ 39672 | consumed samples: 9443840 | consumed tokens: 19340984320 | elapsed time per iteration (s): 0.77 | learning rate: 2.222E-05 | global batch size: 256 | lm loss: 2.059846E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.618 | TFLOPs: 20.24 | +31: iteration 36900/ 39672 | consumed samples: 9446400 | consumed tokens: 19346227200 | elapsed time per iteration (s): 0.81 | learning rate: 2.220E-05 | global batch size: 256 | lm loss: 2.095782E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.895 | TFLOPs: 19.17 | +31: iteration 36910/ 39672 | consumed samples: 9448960 | consumed tokens: 19351470080 | elapsed time per iteration (s): 0.74 | learning rate: 2.219E-05 | global batch size: 256 | lm loss: 2.098930E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.506 | TFLOPs: 20.84 | +31: iteration 36920/ 39672 | consumed samples: 9451520 | consumed tokens: 19356712960 | elapsed time per iteration (s): 0.72 | learning rate: 2.217E-05 | global batch size: 256 | lm loss: 2.069484E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.994 | TFLOPs: 21.54 | +31: iteration 36930/ 39672 | consumed samples: 9454080 | consumed tokens: 19361955840 | elapsed time per iteration (s): 0.84 | learning rate: 2.216E-05 | global batch size: 256 | lm loss: 2.084174E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.651 | TFLOPs: 18.43 | +31: iteration 36940/ 39672 | consumed samples: 9456640 | consumed tokens: 19367198720 | elapsed time per iteration (s): 0.95 | learning rate: 2.214E-05 | global batch size: 256 | lm loss: 2.107146E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 269.950 | TFLOPs: 16.33 | +31: iteration 36950/ 39672 | consumed samples: 9459200 | consumed tokens: 19372441600 | elapsed time per iteration (s): 0.72 | learning rate: 2.213E-05 | global batch size: 256 | lm loss: 2.073326E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 358.029 | TFLOPs: 21.66 | +31: iteration 36960/ 39672 | consumed samples: 9461760 | consumed tokens: 19377684480 | elapsed time per iteration (s): 0.73 | learning rate: 2.211E-05 | global batch size: 256 | lm loss: 2.053334E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 351.355 | TFLOPs: 21.26 | +31: iteration 36970/ 39672 | consumed samples: 9464320 | consumed tokens: 19382927360 | elapsed time per iteration (s): 0.73 | learning rate: 2.210E-05 | global batch size: 256 | lm loss: 2.092625E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.350 | TFLOPs: 21.20 | +31: iteration 36980/ 39672 | consumed samples: 9466880 | consumed tokens: 19388170240 | elapsed time per iteration (s): 0.74 | learning rate: 2.208E-05 | global batch size: 256 | lm loss: 2.081621E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.880 | TFLOPs: 20.80 | +31: iteration 36990/ 39672 | consumed samples: 9469440 | consumed tokens: 19393413120 | elapsed time per iteration (s): 0.70 | learning rate: 2.206E-05 | global batch size: 256 | lm loss: 2.057391E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 363.801 | TFLOPs: 22.01 | +31: iteration 37000/ 39672 | consumed samples: 9472000 | consumed tokens: 19398656000 | elapsed time per iteration (s): 0.74 | learning rate: 2.205E-05 | global batch size: 256 | lm loss: 2.064672E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.336 | TFLOPs: 21.01 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 37000 | lm loss value: 2.070115E+00 | lm loss PPL: 7.925735E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 37010/ 39672 | consumed samples: 9474560 | consumed tokens: 19403898880 | elapsed time per iteration (s): 0.79 | learning rate: 2.203E-05 | global batch size: 256 | lm loss: 2.087567E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.614 | TFLOPs: 19.52 | +31: iteration 37020/ 39672 | consumed samples: 9477120 | consumed tokens: 19409141760 | elapsed time per iteration (s): 0.77 | learning rate: 2.202E-05 | global batch size: 256 | lm loss: 2.048761E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.341 | TFLOPs: 20.11 | +31: iteration 37030/ 39672 | consumed samples: 9479680 | consumed tokens: 19414384640 | elapsed time per iteration (s): 0.82 | learning rate: 2.200E-05 | global batch size: 256 | lm loss: 2.088261E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.885 | TFLOPs: 18.99 | +31: iteration 37040/ 39672 | consumed samples: 9482240 | consumed tokens: 19419627520 | elapsed time per iteration (s): 0.72 | learning rate: 2.199E-05 | global batch size: 256 | lm loss: 2.061934E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.351 | TFLOPs: 21.44 | +31: iteration 37050/ 39672 | consumed samples: 9484800 | consumed tokens: 19424870400 | elapsed time per iteration (s): 0.76 | learning rate: 2.197E-05 | global batch size: 256 | lm loss: 2.085225E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.033 | TFLOPs: 20.33 | +31: iteration 37060/ 39672 | consumed samples: 9487360 | consumed tokens: 19430113280 | elapsed time per iteration (s): 0.76 | learning rate: 2.196E-05 | global batch size: 256 | lm loss: 2.063405E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.799 | TFLOPs: 20.38 | +31: iteration 37070/ 39672 | consumed samples: 9489920 | consumed tokens: 19435356160 | elapsed time per iteration (s): 0.77 | learning rate: 2.194E-05 | global batch size: 256 | lm loss: 2.064793E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.352 | TFLOPs: 20.05 | +31: iteration 37080/ 39672 | consumed samples: 9492480 | consumed tokens: 19440599040 | elapsed time per iteration (s): 0.75 | learning rate: 2.193E-05 | global batch size: 256 | lm loss: 2.066632E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.356 | TFLOPs: 20.71 | +31: iteration 37090/ 39672 | consumed samples: 9495040 | consumed tokens: 19445841920 | elapsed time per iteration (s): 0.79 | learning rate: 2.191E-05 | global batch size: 256 | lm loss: 2.084121E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.511 | TFLOPs: 19.51 | +31: iteration 37100/ 39672 | consumed samples: 9497600 | consumed tokens: 19451084800 | elapsed time per iteration (s): 0.75 | learning rate: 2.190E-05 | global batch size: 256 | lm loss: 2.064641E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.225 | TFLOPs: 20.64 | +31: iteration 37110/ 39672 | consumed samples: 9500160 | consumed tokens: 19456327680 | elapsed time per iteration (s): 0.77 | learning rate: 2.188E-05 | global batch size: 256 | lm loss: 2.088257E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.032 | TFLOPs: 20.21 | +31: iteration 37120/ 39672 | consumed samples: 9502720 | consumed tokens: 19461570560 | elapsed time per iteration (s): 0.84 | learning rate: 2.187E-05 | global batch size: 256 | lm loss: 2.050442E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.032 | TFLOPs: 18.51 | +31: iteration 37130/ 39672 | consumed samples: 9505280 | consumed tokens: 19466813440 | elapsed time per iteration (s): 0.80 | learning rate: 2.186E-05 | global batch size: 256 | lm loss: 2.105536E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.086 | TFLOPs: 19.30 | +31: iteration 37140/ 39672 | consumed samples: 9507840 | consumed tokens: 19472056320 | elapsed time per iteration (s): 0.85 | learning rate: 2.184E-05 | global batch size: 256 | lm loss: 2.060076E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 299.857 | TFLOPs: 18.14 | +31: iteration 37150/ 39672 | consumed samples: 9510400 | consumed tokens: 19477299200 | elapsed time per iteration (s): 0.81 | learning rate: 2.183E-05 | global batch size: 256 | lm loss: 2.073930E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 316.236 | TFLOPs: 19.13 | +31: iteration 37160/ 39672 | consumed samples: 9512960 | consumed tokens: 19482542080 | elapsed time per iteration (s): 0.85 | learning rate: 2.181E-05 | global batch size: 256 | lm loss: 2.085120E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.596 | TFLOPs: 18.31 | +31: iteration 37170/ 39672 | consumed samples: 9515520 | consumed tokens: 19487784960 | elapsed time per iteration (s): 0.82 | learning rate: 2.180E-05 | global batch size: 256 | lm loss: 2.050489E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.401 | TFLOPs: 18.78 | +31: iteration 37180/ 39672 | consumed samples: 9518080 | consumed tokens: 19493027840 | elapsed time per iteration (s): 0.81 | learning rate: 2.178E-05 | global batch size: 256 | lm loss: 2.071547E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.740 | TFLOPs: 19.04 | +31: iteration 37190/ 39672 | consumed samples: 9520640 | consumed tokens: 19498270720 | elapsed time per iteration (s): 0.80 | learning rate: 2.177E-05 | global batch size: 256 | lm loss: 2.065784E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.244 | TFLOPs: 19.31 | +31: iteration 37200/ 39672 | consumed samples: 9523200 | consumed tokens: 19503513600 | elapsed time per iteration (s): 0.80 | learning rate: 2.175E-05 | global batch size: 256 | lm loss: 2.058747E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.886 | TFLOPs: 19.47 | +31: iteration 37210/ 39672 | consumed samples: 9525760 | consumed tokens: 19508756480 | elapsed time per iteration (s): 0.79 | learning rate: 2.174E-05 | global batch size: 256 | lm loss: 2.068134E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.757 | TFLOPs: 19.59 | +31: iteration 37220/ 39672 | consumed samples: 9528320 | consumed tokens: 19513999360 | elapsed time per iteration (s): 0.82 | learning rate: 2.173E-05 | global batch size: 256 | lm loss: 2.078727E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.623 | TFLOPs: 18.97 | +31: iteration 37230/ 39672 | consumed samples: 9530880 | consumed tokens: 19519242240 | elapsed time per iteration (s): 0.77 | learning rate: 2.171E-05 | global batch size: 256 | lm loss: 2.085411E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.814 | TFLOPs: 20.01 | +31: iteration 37240/ 39672 | consumed samples: 9533440 | consumed tokens: 19524485120 | elapsed time per iteration (s): 0.74 | learning rate: 2.170E-05 | global batch size: 256 | lm loss: 2.042125E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.603 | TFLOPs: 20.85 | +31: iteration 37250/ 39672 | consumed samples: 9536000 | consumed tokens: 19529728000 | elapsed time per iteration (s): 0.81 | learning rate: 2.168E-05 | global batch size: 256 | lm loss: 2.080663E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.462 | TFLOPs: 19.21 | +31: iteration 37260/ 39672 | consumed samples: 9538560 | consumed tokens: 19534970880 | elapsed time per iteration (s): 0.79 | learning rate: 2.167E-05 | global batch size: 256 | lm loss: 2.054710E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.331 | TFLOPs: 19.68 | +31: iteration 37270/ 39672 | consumed samples: 9541120 | consumed tokens: 19540213760 | elapsed time per iteration (s): 0.78 | learning rate: 2.166E-05 | global batch size: 256 | lm loss: 2.094756E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.578 | TFLOPs: 19.94 | +31: iteration 37280/ 39672 | consumed samples: 9543680 | consumed tokens: 19545456640 | elapsed time per iteration (s): 0.74 | learning rate: 2.164E-05 | global batch size: 256 | lm loss: 2.077796E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.506 | TFLOPs: 20.84 | +31: iteration 37290/ 39672 | consumed samples: 9546240 | consumed tokens: 19550699520 | elapsed time per iteration (s): 0.75 | learning rate: 2.163E-05 | global batch size: 256 | lm loss: 2.072750E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.953 | TFLOPs: 20.69 | +31: iteration 37300/ 39672 | consumed samples: 9548800 | consumed tokens: 19555942400 | elapsed time per iteration (s): 0.77 | learning rate: 2.162E-05 | global batch size: 256 | lm loss: 2.065784E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.346 | TFLOPs: 20.05 | +31: iteration 37310/ 39672 | consumed samples: 9551360 | consumed tokens: 19561185280 | elapsed time per iteration (s): 0.75 | learning rate: 2.160E-05 | global batch size: 256 | lm loss: 2.072238E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.426 | TFLOPs: 20.66 | +31: iteration 37320/ 39672 | consumed samples: 9553920 | consumed tokens: 19566428160 | elapsed time per iteration (s): 0.74 | learning rate: 2.159E-05 | global batch size: 256 | lm loss: 2.069479E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.585 | TFLOPs: 20.85 | +31: iteration 37330/ 39672 | consumed samples: 9556480 | consumed tokens: 19571671040 | elapsed time per iteration (s): 0.82 | learning rate: 2.158E-05 | global batch size: 256 | lm loss: 2.071434E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.441 | TFLOPs: 18.90 | +31: iteration 37340/ 39672 | consumed samples: 9559040 | consumed tokens: 19576913920 | elapsed time per iteration (s): 0.83 | learning rate: 2.156E-05 | global batch size: 256 | lm loss: 2.057069E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.950 | TFLOPs: 18.63 | +31: iteration 37350/ 39672 | consumed samples: 9561600 | consumed tokens: 19582156800 | elapsed time per iteration (s): 0.89 | learning rate: 2.155E-05 | global batch size: 256 | lm loss: 2.071916E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 287.093 | TFLOPs: 17.37 | +31: iteration 37360/ 39672 | consumed samples: 9564160 | consumed tokens: 19587399680 | elapsed time per iteration (s): 0.77 | learning rate: 2.154E-05 | global batch size: 256 | lm loss: 2.084132E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.838 | TFLOPs: 20.20 | +31: iteration 37370/ 39672 | consumed samples: 9566720 | consumed tokens: 19592642560 | elapsed time per iteration (s): 0.96 | learning rate: 2.152E-05 | global batch size: 256 | lm loss: 2.059893E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 265.627 | TFLOPs: 16.07 | +31: iteration 37380/ 39672 | consumed samples: 9569280 | consumed tokens: 19597885440 | elapsed time per iteration (s): 0.89 | learning rate: 2.151E-05 | global batch size: 256 | lm loss: 2.105886E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 288.484 | TFLOPs: 17.45 | +31: iteration 37390/ 39672 | consumed samples: 9571840 | consumed tokens: 19603128320 | elapsed time per iteration (s): 0.82 | learning rate: 2.150E-05 | global batch size: 256 | lm loss: 2.058750E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 312.628 | TFLOPs: 18.91 | +31: iteration 37400/ 39672 | consumed samples: 9574400 | consumed tokens: 19608371200 | elapsed time per iteration (s): 0.82 | learning rate: 2.148E-05 | global batch size: 256 | lm loss: 2.058956E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.445 | TFLOPs: 18.96 | +31: iteration 37410/ 39672 | consumed samples: 9576960 | consumed tokens: 19613614080 | elapsed time per iteration (s): 0.80 | learning rate: 2.147E-05 | global batch size: 256 | lm loss: 2.036341E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.100 | TFLOPs: 19.43 | +31: iteration 37420/ 39672 | consumed samples: 9579520 | consumed tokens: 19618856960 | elapsed time per iteration (s): 0.76 | learning rate: 2.146E-05 | global batch size: 256 | lm loss: 2.051771E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.808 | TFLOPs: 20.44 | +31: iteration 37430/ 39672 | consumed samples: 9582080 | consumed tokens: 19624099840 | elapsed time per iteration (s): 0.72 | learning rate: 2.144E-05 | global batch size: 256 | lm loss: 2.063699E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.756 | TFLOPs: 21.52 | +31: iteration 37440/ 39672 | consumed samples: 9584640 | consumed tokens: 19629342720 | elapsed time per iteration (s): 0.71 | learning rate: 2.143E-05 | global batch size: 256 | lm loss: 2.052709E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 361.743 | TFLOPs: 21.88 | +31: iteration 37450/ 39672 | consumed samples: 9587200 | consumed tokens: 19634585600 | elapsed time per iteration (s): 0.79 | learning rate: 2.142E-05 | global batch size: 256 | lm loss: 2.079206E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.614 | TFLOPs: 19.52 | +31: iteration 37460/ 39672 | consumed samples: 9589760 | consumed tokens: 19639828480 | elapsed time per iteration (s): 0.78 | learning rate: 2.141E-05 | global batch size: 256 | lm loss: 2.075584E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.662 | TFLOPs: 19.76 | +31: iteration 37470/ 39672 | consumed samples: 9592320 | consumed tokens: 19645071360 | elapsed time per iteration (s): 0.76 | learning rate: 2.139E-05 | global batch size: 256 | lm loss: 2.090913E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.134 | TFLOPs: 20.27 | +31: iteration 37480/ 39672 | consumed samples: 9594880 | consumed tokens: 19650314240 | elapsed time per iteration (s): 0.78 | learning rate: 2.138E-05 | global batch size: 256 | lm loss: 2.066916E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.782 | TFLOPs: 19.89 | +31: iteration 37490/ 39672 | consumed samples: 9597440 | consumed tokens: 19655557120 | elapsed time per iteration (s): 0.75 | learning rate: 2.137E-05 | global batch size: 256 | lm loss: 2.074387E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.768 | TFLOPs: 20.68 | +31: iteration 37500/ 39672 | consumed samples: 9600000 | consumed tokens: 19660800000 | elapsed time per iteration (s): 0.76 | learning rate: 2.136E-05 | global batch size: 256 | lm loss: 2.087492E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.715 | TFLOPs: 20.31 | +31: iteration 37510/ 39672 | consumed samples: 9602560 | consumed tokens: 19666042880 | elapsed time per iteration (s): 0.76 | learning rate: 2.134E-05 | global batch size: 256 | lm loss: 2.077741E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.002 | TFLOPs: 20.33 | +31: iteration 37520/ 39672 | consumed samples: 9605120 | consumed tokens: 19671285760 | elapsed time per iteration (s): 0.72 | learning rate: 2.133E-05 | global batch size: 256 | lm loss: 2.043000E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.978 | TFLOPs: 21.54 | +31: iteration 37530/ 39672 | consumed samples: 9607680 | consumed tokens: 19676528640 | elapsed time per iteration (s): 0.80 | learning rate: 2.132E-05 | global batch size: 256 | lm loss: 2.067532E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.621 | TFLOPs: 19.34 | +31: iteration 37540/ 39672 | consumed samples: 9610240 | consumed tokens: 19681771520 | elapsed time per iteration (s): 0.90 | learning rate: 2.131E-05 | global batch size: 256 | lm loss: 2.009626E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 283.940 | TFLOPs: 17.18 | +31: iteration 37550/ 39672 | consumed samples: 9612800 | consumed tokens: 19687014400 | elapsed time per iteration (s): 0.85 | learning rate: 2.129E-05 | global batch size: 256 | lm loss: 2.053499E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.092 | TFLOPs: 18.28 | +31: iteration 37560/ 39672 | consumed samples: 9615360 | consumed tokens: 19692257280 | elapsed time per iteration (s): 0.89 | learning rate: 2.128E-05 | global batch size: 256 | lm loss: 2.035068E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 286.753 | TFLOPs: 17.35 | +31: iteration 37570/ 39672 | consumed samples: 9617920 | consumed tokens: 19697500160 | elapsed time per iteration (s): 0.95 | learning rate: 2.127E-05 | global batch size: 256 | lm loss: 2.067244E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 269.136 | TFLOPs: 16.28 | +31: iteration 37580/ 39672 | consumed samples: 9620480 | consumed tokens: 19702743040 | elapsed time per iteration (s): 0.84 | learning rate: 2.126E-05 | global batch size: 256 | lm loss: 2.095924E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.613 | TFLOPs: 18.37 | +31: iteration 37590/ 39672 | consumed samples: 9623040 | consumed tokens: 19707985920 | elapsed time per iteration (s): 0.79 | learning rate: 2.125E-05 | global batch size: 256 | lm loss: 2.053191E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.295 | TFLOPs: 19.50 | +31: iteration 37600/ 39672 | consumed samples: 9625600 | consumed tokens: 19713228800 | elapsed time per iteration (s): 0.73 | learning rate: 2.123E-05 | global batch size: 256 | lm loss: 2.088359E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.181 | TFLOPs: 21.31 | +31: iteration 37610/ 39672 | consumed samples: 9628160 | consumed tokens: 19718471680 | elapsed time per iteration (s): 0.75 | learning rate: 2.122E-05 | global batch size: 256 | lm loss: 2.067570E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.862 | TFLOPs: 20.62 | +31: iteration 37620/ 39672 | consumed samples: 9630720 | consumed tokens: 19723714560 | elapsed time per iteration (s): 0.80 | learning rate: 2.121E-05 | global batch size: 256 | lm loss: 2.091599E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.913 | TFLOPs: 19.29 | +31: iteration 37630/ 39672 | consumed samples: 9633280 | consumed tokens: 19728957440 | elapsed time per iteration (s): 0.75 | learning rate: 2.120E-05 | global batch size: 256 | lm loss: 2.049813E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.236 | TFLOPs: 20.70 | +31: iteration 37640/ 39672 | consumed samples: 9635840 | consumed tokens: 19734200320 | elapsed time per iteration (s): 0.77 | learning rate: 2.119E-05 | global batch size: 256 | lm loss: 2.063643E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.116 | TFLOPs: 20.03 | +31: iteration 37650/ 39672 | consumed samples: 9638400 | consumed tokens: 19739443200 | elapsed time per iteration (s): 0.81 | learning rate: 2.118E-05 | global batch size: 256 | lm loss: 2.067937E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.048 | TFLOPs: 19.18 | +31: iteration 37660/ 39672 | consumed samples: 9640960 | consumed tokens: 19744686080 | elapsed time per iteration (s): 0.74 | learning rate: 2.116E-05 | global batch size: 256 | lm loss: 2.051214E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.319 | TFLOPs: 20.89 | +31: iteration 37670/ 39672 | consumed samples: 9643520 | consumed tokens: 19749928960 | elapsed time per iteration (s): 0.80 | learning rate: 2.115E-05 | global batch size: 256 | lm loss: 2.047905E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.191 | TFLOPs: 19.31 | +31: iteration 37680/ 39672 | consumed samples: 9646080 | consumed tokens: 19755171840 | elapsed time per iteration (s): 0.77 | learning rate: 2.114E-05 | global batch size: 256 | lm loss: 2.067497E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.595 | TFLOPs: 20.24 | +31: iteration 37690/ 39672 | consumed samples: 9648640 | consumed tokens: 19760414720 | elapsed time per iteration (s): 0.74 | learning rate: 2.113E-05 | global batch size: 256 | lm loss: 2.039010E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.744 | TFLOPs: 21.04 | +31: iteration 37700/ 39672 | consumed samples: 9651200 | consumed tokens: 19765657600 | elapsed time per iteration (s): 0.73 | learning rate: 2.112E-05 | global batch size: 256 | lm loss: 2.104480E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.154 | TFLOPs: 21.18 | +31: iteration 37710/ 39672 | consumed samples: 9653760 | consumed tokens: 19770900480 | elapsed time per iteration (s): 0.75 | learning rate: 2.111E-05 | global batch size: 256 | lm loss: 2.102230E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.116 | TFLOPs: 20.64 | +31: iteration 37720/ 39672 | consumed samples: 9656320 | consumed tokens: 19776143360 | elapsed time per iteration (s): 0.72 | learning rate: 2.110E-05 | global batch size: 256 | lm loss: 2.095783E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.495 | TFLOPs: 21.51 | +31: iteration 37730/ 39672 | consumed samples: 9658880 | consumed tokens: 19781386240 | elapsed time per iteration (s): 0.75 | learning rate: 2.108E-05 | global batch size: 256 | lm loss: 2.072566E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.652 | TFLOPs: 20.67 | +31: iteration 37740/ 39672 | consumed samples: 9661440 | consumed tokens: 19786629120 | elapsed time per iteration (s): 0.74 | learning rate: 2.107E-05 | global batch size: 256 | lm loss: 2.077194E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.164 | TFLOPs: 20.88 | +31: iteration 37750/ 39672 | consumed samples: 9664000 | consumed tokens: 19791872000 | elapsed time per iteration (s): 1.39 | learning rate: 2.106E-05 | global batch size: 256 | lm loss: 2.068768E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 184.709 | TFLOPs: 11.17 | +31: iteration 37760/ 39672 | consumed samples: 9666560 | consumed tokens: 19797114880 | elapsed time per iteration (s): 1.61 | learning rate: 2.105E-05 | global batch size: 256 | lm loss: 2.062793E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 158.926 | TFLOPs: 9.61 | +31: iteration 37770/ 39672 | consumed samples: 9669120 | consumed tokens: 19802357760 | elapsed time per iteration (s): 1.33 | learning rate: 2.104E-05 | global batch size: 256 | lm loss: 2.061550E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.934 | TFLOPs: 11.67 | +31: iteration 37780/ 39672 | consumed samples: 9671680 | consumed tokens: 19807600640 | elapsed time per iteration (s): 0.81 | learning rate: 2.103E-05 | global batch size: 256 | lm loss: 2.071429E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.312 | TFLOPs: 19.02 | +31: iteration 37790/ 39672 | consumed samples: 9674240 | consumed tokens: 19812843520 | elapsed time per iteration (s): 0.86 | learning rate: 2.102E-05 | global batch size: 256 | lm loss: 2.059787E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 297.421 | TFLOPs: 17.99 | +31: iteration 37800/ 39672 | consumed samples: 9676800 | consumed tokens: 19818086400 | elapsed time per iteration (s): 0.80 | learning rate: 2.101E-05 | global batch size: 256 | lm loss: 2.053383E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.427 | TFLOPs: 19.26 | +31: iteration 37810/ 39672 | consumed samples: 9679360 | consumed tokens: 19823329280 | elapsed time per iteration (s): 0.75 | learning rate: 2.100E-05 | global batch size: 256 | lm loss: 2.031761E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.034 | TFLOPs: 20.75 | +31: iteration 37820/ 39672 | consumed samples: 9681920 | consumed tokens: 19828572160 | elapsed time per iteration (s): 0.94 | learning rate: 2.099E-05 | global batch size: 256 | lm loss: 2.057895E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 271.138 | TFLOPs: 16.40 | +31: iteration 37830/ 39672 | consumed samples: 9684480 | consumed tokens: 19833815040 | elapsed time per iteration (s): 0.85 | learning rate: 2.098E-05 | global batch size: 256 | lm loss: 2.094095E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.662 | TFLOPs: 18.31 | +31: iteration 37840/ 39672 | consumed samples: 9687040 | consumed tokens: 19839057920 | elapsed time per iteration (s): 1.11 | learning rate: 2.097E-05 | global batch size: 256 | lm loss: 2.045244E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 231.417 | TFLOPs: 14.00 | +31: iteration 37850/ 39672 | consumed samples: 9689600 | consumed tokens: 19844300800 | elapsed time per iteration (s): 0.91 | learning rate: 2.095E-05 | global batch size: 256 | lm loss: 2.062433E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 280.569 | TFLOPs: 16.97 | +31: iteration 37860/ 39672 | consumed samples: 9692160 | consumed tokens: 19849543680 | elapsed time per iteration (s): 0.85 | learning rate: 2.094E-05 | global batch size: 256 | lm loss: 2.084574E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.953 | TFLOPs: 18.27 | +31: iteration 37870/ 39672 | consumed samples: 9694720 | consumed tokens: 19854786560 | elapsed time per iteration (s): 0.77 | learning rate: 2.093E-05 | global batch size: 256 | lm loss: 2.074440E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.529 | TFLOPs: 20.00 | +31: iteration 37880/ 39672 | consumed samples: 9697280 | consumed tokens: 19860029440 | elapsed time per iteration (s): 0.74 | learning rate: 2.092E-05 | global batch size: 256 | lm loss: 2.072085E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.512 | TFLOPs: 20.84 | +31: iteration 37890/ 39672 | consumed samples: 9699840 | consumed tokens: 19865272320 | elapsed time per iteration (s): 0.74 | learning rate: 2.091E-05 | global batch size: 256 | lm loss: 2.081064E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 345.693 | TFLOPs: 20.91 | +31: iteration 37900/ 39672 | consumed samples: 9702400 | consumed tokens: 19870515200 | elapsed time per iteration (s): 0.78 | learning rate: 2.090E-05 | global batch size: 256 | lm loss: 2.049056E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.986 | TFLOPs: 19.84 | +31: iteration 37910/ 39672 | consumed samples: 9704960 | consumed tokens: 19875758080 | elapsed time per iteration (s): 0.78 | learning rate: 2.089E-05 | global batch size: 256 | lm loss: 2.056380E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.840 | TFLOPs: 19.77 | +31: iteration 37920/ 39672 | consumed samples: 9707520 | consumed tokens: 19881000960 | elapsed time per iteration (s): 0.81 | learning rate: 2.088E-05 | global batch size: 256 | lm loss: 2.097348E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.188 | TFLOPs: 19.01 | +31: iteration 37930/ 39672 | consumed samples: 9710080 | consumed tokens: 19886243840 | elapsed time per iteration (s): 0.74 | learning rate: 2.087E-05 | global batch size: 256 | lm loss: 2.052665E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.346 | TFLOPs: 20.83 | +31: iteration 37940/ 39672 | consumed samples: 9712640 | consumed tokens: 19891486720 | elapsed time per iteration (s): 1.52 | learning rate: 2.086E-05 | global batch size: 256 | lm loss: 2.068268E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 168.341 | TFLOPs: 10.18 | +31: iteration 37950/ 39672 | consumed samples: 9715200 | consumed tokens: 19896729600 | elapsed time per iteration (s): 1.69 | learning rate: 2.085E-05 | global batch size: 256 | lm loss: 2.081459E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 151.292 | TFLOPs: 9.15 | +31: iteration 37960/ 39672 | consumed samples: 9717760 | consumed tokens: 19901972480 | elapsed time per iteration (s): 1.29 | learning rate: 2.084E-05 | global batch size: 256 | lm loss: 2.081897E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.818 | TFLOPs: 12.03 | +31: iteration 37970/ 39672 | consumed samples: 9720320 | consumed tokens: 19907215360 | elapsed time per iteration (s): 0.97 | learning rate: 2.083E-05 | global batch size: 256 | lm loss: 2.069196E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 263.853 | TFLOPs: 15.96 | +31: iteration 37980/ 39672 | consumed samples: 9722880 | consumed tokens: 19912458240 | elapsed time per iteration (s): 0.80 | learning rate: 2.082E-05 | global batch size: 256 | lm loss: 2.056683E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.458 | TFLOPs: 19.27 | +31: iteration 37990/ 39672 | consumed samples: 9725440 | consumed tokens: 19917701120 | elapsed time per iteration (s): 0.84 | learning rate: 2.081E-05 | global batch size: 256 | lm loss: 2.073984E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.983 | TFLOPs: 18.45 | + 0: [2022-11-30 18:27:33,046] [INFO] [logging.py:68:log_dist] [Rank 0] step=38000, skipped=0, lr=[2.080449216001019e-05, 2.080449216001019e-05, 2.080449216001019e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 38000 loss: 2.1476 iter time (s): 1.112 samples/sec: 230.156 +31: iteration 38000/ 39672 | consumed samples: 9728000 | consumed tokens: 19922944000 | elapsed time per iteration (s): 2.37 | learning rate: 2.080E-05 | global batch size: 256 | lm loss: 2.070399E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 107.872 | TFLOPs: 6.53 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 38000 | lm loss value: 2.078504E+00 | lm loss PPL: 7.992506E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 38010/ 39672 | consumed samples: 9730560 | consumed tokens: 19928186880 | elapsed time per iteration (s): 3.95 | learning rate: 2.079E-05 | global batch size: 256 | lm loss: 2.066539E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 64.878 | TFLOPs: 3.92 | +31: iteration 38020/ 39672 | consumed samples: 9733120 | consumed tokens: 19933429760 | elapsed time per iteration (s): 4.53 | learning rate: 2.079E-05 | global batch size: 256 | lm loss: 2.027579E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 56.521 | TFLOPs: 3.42 | +31: iteration 38030/ 39672 | consumed samples: 9735680 | consumed tokens: 19938672640 | elapsed time per iteration (s): 5.23 | learning rate: 2.078E-05 | global batch size: 256 | lm loss: 2.067339E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 48.984 | TFLOPs: 2.96 | +31: iteration 38040/ 39672 | consumed samples: 9738240 | consumed tokens: 19943915520 | elapsed time per iteration (s): 2.99 | learning rate: 2.077E-05 | global batch size: 256 | lm loss: 2.039222E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.605 | TFLOPs: 5.18 | +31: iteration 38050/ 39672 | consumed samples: 9740800 | consumed tokens: 19949158400 | elapsed time per iteration (s): 3.51 | learning rate: 2.076E-05 | global batch size: 256 | lm loss: 2.076380E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 72.967 | TFLOPs: 4.41 | +31: iteration 38060/ 39672 | consumed samples: 9743360 | consumed tokens: 19954401280 | elapsed time per iteration (s): 1.06 | learning rate: 2.075E-05 | global batch size: 256 | lm loss: 2.067217E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 241.327 | TFLOPs: 14.60 | +31: iteration 38070/ 39672 | consumed samples: 9745920 | consumed tokens: 19959644160 | elapsed time per iteration (s): 1.09 | learning rate: 2.074E-05 | global batch size: 256 | lm loss: 2.055898E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 234.105 | TFLOPs: 14.16 | +31: iteration 38080/ 39672 | consumed samples: 9748480 | consumed tokens: 19964887040 | elapsed time per iteration (s): 0.91 | learning rate: 2.073E-05 | global batch size: 256 | lm loss: 2.054198E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 282.446 | TFLOPs: 17.09 | +31: iteration 38090/ 39672 | consumed samples: 9751040 | consumed tokens: 19970129920 | elapsed time per iteration (s): 0.85 | learning rate: 2.072E-05 | global batch size: 256 | lm loss: 2.052506E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.002 | TFLOPs: 18.21 | +31: iteration 38100/ 39672 | consumed samples: 9753600 | consumed tokens: 19975372800 | elapsed time per iteration (s): 1.13 | learning rate: 2.071E-05 | global batch size: 256 | lm loss: 2.060717E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.935 | TFLOPs: 13.73 | +31: iteration 38110/ 39672 | consumed samples: 9756160 | consumed tokens: 19980615680 | elapsed time per iteration (s): 1.18 | learning rate: 2.070E-05 | global batch size: 256 | lm loss: 2.074575E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.935 | TFLOPs: 13.12 | +31: iteration 38120/ 39672 | consumed samples: 9758720 | consumed tokens: 19985858560 | elapsed time per iteration (s): 4.67 | learning rate: 2.069E-05 | global batch size: 256 | lm loss: 2.078157E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 54.850 | TFLOPs: 3.32 | +31: iteration 38130/ 39672 | consumed samples: 9761280 | consumed tokens: 19991101440 | elapsed time per iteration (s): 6.61 | learning rate: 2.068E-05 | global batch size: 256 | lm loss: 2.084049E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 38.707 | TFLOPs: 2.34 | +31: iteration 38140/ 39672 | consumed samples: 9763840 | consumed tokens: 19996344320 | elapsed time per iteration (s): 7.95 | learning rate: 2.068E-05 | global batch size: 256 | lm loss: 2.088610E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 32.187 | TFLOPs: 1.95 | +31: iteration 38150/ 39672 | consumed samples: 9766400 | consumed tokens: 20001587200 | elapsed time per iteration (s): 4.37 | learning rate: 2.067E-05 | global batch size: 256 | lm loss: 2.075387E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 58.590 | TFLOPs: 3.54 | +31: iteration 38160/ 39672 | consumed samples: 9768960 | consumed tokens: 20006830080 | elapsed time per iteration (s): 2.07 | learning rate: 2.066E-05 | global batch size: 256 | lm loss: 2.074570E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 123.639 | TFLOPs: 7.48 | +31: iteration 38170/ 39672 | consumed samples: 9771520 | consumed tokens: 20012072960 | elapsed time per iteration (s): 1.72 | learning rate: 2.065E-05 | global batch size: 256 | lm loss: 2.101767E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 148.808 | TFLOPs: 9.00 | +31: iteration 38180/ 39672 | consumed samples: 9774080 | consumed tokens: 20017315840 | elapsed time per iteration (s): 3.20 | learning rate: 2.064E-05 | global batch size: 256 | lm loss: 2.074723E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 80.025 | TFLOPs: 4.84 | +31: iteration 38190/ 39672 | consumed samples: 9776640 | consumed tokens: 20022558720 | elapsed time per iteration (s): 2.03 | learning rate: 2.063E-05 | global batch size: 256 | lm loss: 2.080288E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 125.801 | TFLOPs: 7.61 | +31: iteration 38200/ 39672 | consumed samples: 9779200 | consumed tokens: 20027801600 | elapsed time per iteration (s): 0.99 | learning rate: 2.062E-05 | global batch size: 256 | lm loss: 2.067554E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 259.862 | TFLOPs: 15.72 | +31: iteration 38210/ 39672 | consumed samples: 9781760 | consumed tokens: 20033044480 | elapsed time per iteration (s): 1.17 | learning rate: 2.062E-05 | global batch size: 256 | lm loss: 2.090651E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.467 | TFLOPs: 13.22 | +31: iteration 38220/ 39672 | consumed samples: 9784320 | consumed tokens: 20038287360 | elapsed time per iteration (s): 0.85 | learning rate: 2.061E-05 | global batch size: 256 | lm loss: 2.058118E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.691 | TFLOPs: 18.31 | +31: iteration 38230/ 39672 | consumed samples: 9786880 | consumed tokens: 20043530240 | elapsed time per iteration (s): 0.80 | learning rate: 2.060E-05 | global batch size: 256 | lm loss: 2.067096E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 321.995 | TFLOPs: 19.48 | +31: iteration 38240/ 39672 | consumed samples: 9789440 | consumed tokens: 20048773120 | elapsed time per iteration (s): 0.79 | learning rate: 2.059E-05 | global batch size: 256 | lm loss: 2.111849E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 322.152 | TFLOPs: 19.49 | +31: iteration 38250/ 39672 | consumed samples: 9792000 | consumed tokens: 20054016000 | elapsed time per iteration (s): 1.02 | learning rate: 2.058E-05 | global batch size: 256 | lm loss: 2.084810E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 251.480 | TFLOPs: 15.21 | +31: iteration 38260/ 39672 | consumed samples: 9794560 | consumed tokens: 20059258880 | elapsed time per iteration (s): 0.91 | learning rate: 2.057E-05 | global batch size: 256 | lm loss: 2.046771E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 279.938 | TFLOPs: 16.94 | +31: iteration 38270/ 39672 | consumed samples: 9797120 | consumed tokens: 20064501760 | elapsed time per iteration (s): 0.83 | learning rate: 2.057E-05 | global batch size: 256 | lm loss: 2.079545E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 309.300 | TFLOPs: 18.71 | +31: iteration 38280/ 39672 | consumed samples: 9799680 | consumed tokens: 20069744640 | elapsed time per iteration (s): 3.53 | learning rate: 2.056E-05 | global batch size: 256 | lm loss: 2.061535E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 72.465 | TFLOPs: 4.38 | +31: iteration 38290/ 39672 | consumed samples: 9802240 | consumed tokens: 20074987520 | elapsed time per iteration (s): 4.41 | learning rate: 2.055E-05 | global batch size: 256 | lm loss: 2.073924E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 58.007 | TFLOPs: 3.51 | +31: iteration 38300/ 39672 | consumed samples: 9804800 | consumed tokens: 20080230400 | elapsed time per iteration (s): 6.45 | learning rate: 2.054E-05 | global batch size: 256 | lm loss: 2.060276E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 39.692 | TFLOPs: 2.40 | +31: iteration 38310/ 39672 | consumed samples: 9807360 | consumed tokens: 20085473280 | elapsed time per iteration (s): 3.72 | learning rate: 2.053E-05 | global batch size: 256 | lm loss: 2.079816E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 68.812 | TFLOPs: 4.16 | +31: iteration 38320/ 39672 | consumed samples: 9809920 | consumed tokens: 20090716160 | elapsed time per iteration (s): 1.51 | learning rate: 2.053E-05 | global batch size: 256 | lm loss: 2.058193E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 169.078 | TFLOPs: 10.23 | +31: iteration 38330/ 39672 | consumed samples: 9812480 | consumed tokens: 20095959040 | elapsed time per iteration (s): 1.35 | learning rate: 2.052E-05 | global batch size: 256 | lm loss: 2.029445E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 189.745 | TFLOPs: 11.48 | +31: iteration 38340/ 39672 | consumed samples: 9815040 | consumed tokens: 20101201920 | elapsed time per iteration (s): 1.31 | learning rate: 2.051E-05 | global batch size: 256 | lm loss: 2.062444E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.052 | TFLOPs: 11.86 | +31: iteration 38350/ 39672 | consumed samples: 9817600 | consumed tokens: 20106444800 | elapsed time per iteration (s): 1.53 | learning rate: 2.050E-05 | global batch size: 256 | lm loss: 2.080571E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 167.762 | TFLOPs: 10.15 | +31: iteration 38360/ 39672 | consumed samples: 9820160 | consumed tokens: 20111687680 | elapsed time per iteration (s): 1.50 | learning rate: 2.050E-05 | global batch size: 256 | lm loss: 2.061576E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 171.226 | TFLOPs: 10.36 | +31: iteration 38370/ 39672 | consumed samples: 9822720 | consumed tokens: 20116930560 | elapsed time per iteration (s): 1.37 | learning rate: 2.049E-05 | global batch size: 256 | lm loss: 2.050465E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 186.771 | TFLOPs: 11.30 | +31: iteration 38380/ 39672 | consumed samples: 9825280 | consumed tokens: 20122173440 | elapsed time per iteration (s): 1.39 | learning rate: 2.048E-05 | global batch size: 256 | lm loss: 2.076179E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 184.252 | TFLOPs: 11.15 | +31: iteration 38390/ 39672 | consumed samples: 9827840 | consumed tokens: 20127416320 | elapsed time per iteration (s): 10.22 | learning rate: 2.047E-05 | global batch size: 256 | lm loss: 2.078413E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 25.049 | TFLOPs: 1.52 | +31: iteration 38400/ 39672 | consumed samples: 9830400 | consumed tokens: 20132659200 | elapsed time per iteration (s): 11.21 | learning rate: 2.047E-05 | global batch size: 256 | lm loss: 2.070126E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 22.828 | TFLOPs: 1.38 | +31: iteration 38410/ 39672 | consumed samples: 9832960 | consumed tokens: 20137902080 | elapsed time per iteration (s): 9.33 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 2.060017E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 27.433 | TFLOPs: 1.66 | +31: iteration 38420/ 39672 | consumed samples: 9835520 | consumed tokens: 20143144960 | elapsed time per iteration (s): 9.80 | learning rate: 2.045E-05 | global batch size: 256 | lm loss: 2.093584E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 26.120 | TFLOPs: 1.58 | +31: iteration 38430/ 39672 | consumed samples: 9838080 | consumed tokens: 20148387840 | elapsed time per iteration (s): 7.03 | learning rate: 2.044E-05 | global batch size: 256 | lm loss: 2.064281E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 36.412 | TFLOPs: 2.20 | +31: iteration 38440/ 39672 | consumed samples: 9840640 | consumed tokens: 20153630720 | elapsed time per iteration (s): 3.26 | learning rate: 2.044E-05 | global batch size: 256 | lm loss: 2.076244E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 78.479 | TFLOPs: 4.75 | +31: iteration 38450/ 39672 | consumed samples: 9843200 | consumed tokens: 20158873600 | elapsed time per iteration (s): 0.80 | learning rate: 2.043E-05 | global batch size: 256 | lm loss: 2.074228E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.133 | TFLOPs: 19.37 | +31: iteration 38460/ 39672 | consumed samples: 9845760 | consumed tokens: 20164116480 | elapsed time per iteration (s): 0.83 | learning rate: 2.042E-05 | global batch size: 256 | lm loss: 2.055548E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.752 | TFLOPs: 18.62 | +31: iteration 38470/ 39672 | consumed samples: 9848320 | consumed tokens: 20169359360 | elapsed time per iteration (s): 0.76 | learning rate: 2.042E-05 | global batch size: 256 | lm loss: 2.037950E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.883 | TFLOPs: 20.32 | +31: iteration 38480/ 39672 | consumed samples: 9850880 | consumed tokens: 20174602240 | elapsed time per iteration (s): 0.85 | learning rate: 2.041E-05 | global batch size: 256 | lm loss: 2.076357E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.691 | TFLOPs: 18.25 | +31: iteration 38490/ 39672 | consumed samples: 9853440 | consumed tokens: 20179845120 | elapsed time per iteration (s): 0.81 | learning rate: 2.040E-05 | global batch size: 256 | lm loss: 2.070132E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.126 | TFLOPs: 19.00 | +31: iteration 38500/ 39672 | consumed samples: 9856000 | consumed tokens: 20185088000 | elapsed time per iteration (s): 1.54 | learning rate: 2.040E-05 | global batch size: 256 | lm loss: 2.073276E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 166.018 | TFLOPs: 10.04 | +31: iteration 38510/ 39672 | consumed samples: 9858560 | consumed tokens: 20190330880 | elapsed time per iteration (s): 0.85 | learning rate: 2.039E-05 | global batch size: 256 | lm loss: 2.070543E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.644 | TFLOPs: 18.19 | +31: iteration 38520/ 39672 | consumed samples: 9861120 | consumed tokens: 20195573760 | elapsed time per iteration (s): 0.82 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 2.089075E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.161 | TFLOPs: 18.95 | +31: iteration 38530/ 39672 | consumed samples: 9863680 | consumed tokens: 20200816640 | elapsed time per iteration (s): 0.79 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 2.100021E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.052 | TFLOPs: 19.73 | +31: iteration 38540/ 39672 | consumed samples: 9866240 | consumed tokens: 20206059520 | elapsed time per iteration (s): 3.43 | learning rate: 2.037E-05 | global batch size: 256 | lm loss: 2.042882E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 74.724 | TFLOPs: 4.52 | +31: iteration 38550/ 39672 | consumed samples: 9868800 | consumed tokens: 20211302400 | elapsed time per iteration (s): 4.58 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 2.076858E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 55.844 | TFLOPs: 3.38 | +31: iteration 38560/ 39672 | consumed samples: 9871360 | consumed tokens: 20216545280 | elapsed time per iteration (s): 6.30 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 2.044855E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 40.631 | TFLOPs: 2.46 | +31: iteration 38570/ 39672 | consumed samples: 9873920 | consumed tokens: 20221788160 | elapsed time per iteration (s): 2.51 | learning rate: 2.035E-05 | global batch size: 256 | lm loss: 2.072078E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 101.818 | TFLOPs: 6.16 | +31: iteration 38580/ 39672 | consumed samples: 9876480 | consumed tokens: 20227031040 | elapsed time per iteration (s): 1.20 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 2.038805E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.828 | TFLOPs: 12.88 | +31: iteration 38590/ 39672 | consumed samples: 9879040 | consumed tokens: 20232273920 | elapsed time per iteration (s): 1.02 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 2.071746E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 251.310 | TFLOPs: 15.20 | +31: iteration 38600/ 39672 | consumed samples: 9881600 | consumed tokens: 20237516800 | elapsed time per iteration (s): 1.13 | learning rate: 2.033E-05 | global batch size: 256 | lm loss: 2.071991E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.631 | TFLOPs: 13.65 | +31: iteration 38610/ 39672 | consumed samples: 9884160 | consumed tokens: 20242759680 | elapsed time per iteration (s): 1.12 | learning rate: 2.033E-05 | global batch size: 256 | lm loss: 2.092863E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.281 | TFLOPs: 13.87 | +31: iteration 38620/ 39672 | consumed samples: 9886720 | consumed tokens: 20248002560 | elapsed time per iteration (s): 1.08 | learning rate: 2.032E-05 | global batch size: 256 | lm loss: 2.037401E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 237.922 | TFLOPs: 14.39 | +31: iteration 38630/ 39672 | consumed samples: 9889280 | consumed tokens: 20253245440 | elapsed time per iteration (s): 1.03 | learning rate: 2.031E-05 | global batch size: 256 | lm loss: 2.064693E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 247.819 | TFLOPs: 14.99 | +31: iteration 38640/ 39672 | consumed samples: 9891840 | consumed tokens: 20258488320 | elapsed time per iteration (s): 0.92 | learning rate: 2.031E-05 | global batch size: 256 | lm loss: 2.067118E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 277.863 | TFLOPs: 16.81 | +31: iteration 38650/ 39672 | consumed samples: 9894400 | consumed tokens: 20263731200 | elapsed time per iteration (s): 0.82 | learning rate: 2.030E-05 | global batch size: 256 | lm loss: 2.062777E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.857 | TFLOPs: 18.87 | +31: iteration 38660/ 39672 | consumed samples: 9896960 | consumed tokens: 20268974080 | elapsed time per iteration (s): 1.01 | learning rate: 2.030E-05 | global batch size: 256 | lm loss: 2.061498E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 253.125 | TFLOPs: 15.31 | +31: iteration 38670/ 39672 | consumed samples: 9899520 | consumed tokens: 20274216960 | elapsed time per iteration (s): 0.91 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 2.066625E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 281.265 | TFLOPs: 17.02 | +31: iteration 38680/ 39672 | consumed samples: 9902080 | consumed tokens: 20279459840 | elapsed time per iteration (s): 0.98 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 2.080271E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 260.546 | TFLOPs: 15.76 | +31: iteration 38690/ 39672 | consumed samples: 9904640 | consumed tokens: 20284702720 | elapsed time per iteration (s): 0.80 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 2.079049E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 320.611 | TFLOPs: 19.40 | +31: iteration 38700/ 39672 | consumed samples: 9907200 | consumed tokens: 20289945600 | elapsed time per iteration (s): 0.78 | learning rate: 2.027E-05 | global batch size: 256 | lm loss: 2.060267E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.559 | TFLOPs: 19.82 | +31: iteration 38710/ 39672 | consumed samples: 9909760 | consumed tokens: 20295188480 | elapsed time per iteration (s): 0.98 | learning rate: 2.027E-05 | global batch size: 256 | lm loss: 2.077702E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 260.003 | TFLOPs: 15.73 | +31: iteration 38720/ 39672 | consumed samples: 9912320 | consumed tokens: 20300431360 | elapsed time per iteration (s): 0.82 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.096528E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.564 | TFLOPs: 18.79 | +31: iteration 38730/ 39672 | consumed samples: 9914880 | consumed tokens: 20305674240 | elapsed time per iteration (s): 0.93 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.052378E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 276.120 | TFLOPs: 16.70 | +31: iteration 38740/ 39672 | consumed samples: 9917440 | consumed tokens: 20310917120 | elapsed time per iteration (s): 0.96 | learning rate: 2.025E-05 | global batch size: 256 | lm loss: 2.033198E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 267.108 | TFLOPs: 16.16 | +31: iteration 38750/ 39672 | consumed samples: 9920000 | consumed tokens: 20316160000 | elapsed time per iteration (s): 0.97 | learning rate: 2.025E-05 | global batch size: 256 | lm loss: 2.058618E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 263.861 | TFLOPs: 15.96 | +31: iteration 38760/ 39672 | consumed samples: 9922560 | consumed tokens: 20321402880 | elapsed time per iteration (s): 0.92 | learning rate: 2.024E-05 | global batch size: 256 | lm loss: 2.049224E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 278.437 | TFLOPs: 16.84 | +31: iteration 38770/ 39672 | consumed samples: 9925120 | consumed tokens: 20326645760 | elapsed time per iteration (s): 0.82 | learning rate: 2.023E-05 | global batch size: 256 | lm loss: 2.044465E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.693 | TFLOPs: 18.98 | +31: iteration 38780/ 39672 | consumed samples: 9927680 | consumed tokens: 20331888640 | elapsed time per iteration (s): 0.88 | learning rate: 2.023E-05 | global batch size: 256 | lm loss: 2.057020E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 290.934 | TFLOPs: 17.60 | +31: iteration 38790/ 39672 | consumed samples: 9930240 | consumed tokens: 20337131520 | elapsed time per iteration (s): 4.62 | learning rate: 2.022E-05 | global batch size: 256 | lm loss: 2.069120E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 55.370 | TFLOPs: 3.35 | +31: iteration 38800/ 39672 | consumed samples: 9932800 | consumed tokens: 20342374400 | elapsed time per iteration (s): 8.22 | learning rate: 2.022E-05 | global batch size: 256 | lm loss: 2.063556E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 31.161 | TFLOPs: 1.89 | +31: iteration 38810/ 39672 | consumed samples: 9935360 | consumed tokens: 20347617280 | elapsed time per iteration (s): 5.72 | learning rate: 2.021E-05 | global batch size: 256 | lm loss: 2.058694E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 44.725 | TFLOPs: 2.71 | +31: iteration 38820/ 39672 | consumed samples: 9937920 | consumed tokens: 20352860160 | elapsed time per iteration (s): 1.08 | learning rate: 2.021E-05 | global batch size: 256 | lm loss: 2.073167E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 236.253 | TFLOPs: 14.29 | +31: iteration 38830/ 39672 | consumed samples: 9940480 | consumed tokens: 20358103040 | elapsed time per iteration (s): 1.19 | learning rate: 2.020E-05 | global batch size: 256 | lm loss: 2.077197E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.287 | TFLOPs: 13.02 | +31: iteration 38840/ 39672 | consumed samples: 9943040 | consumed tokens: 20363345920 | elapsed time per iteration (s): 1.10 | learning rate: 2.020E-05 | global batch size: 256 | lm loss: 2.057209E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 233.418 | TFLOPs: 14.12 | +31: iteration 38850/ 39672 | consumed samples: 9945600 | consumed tokens: 20368588800 | elapsed time per iteration (s): 0.99 | learning rate: 2.019E-05 | global batch size: 256 | lm loss: 2.049010E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 257.287 | TFLOPs: 15.57 | +31: iteration 38860/ 39672 | consumed samples: 9948160 | consumed tokens: 20373831680 | elapsed time per iteration (s): 0.91 | learning rate: 2.019E-05 | global batch size: 256 | lm loss: 2.056476E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 281.086 | TFLOPs: 17.00 | +31: iteration 38870/ 39672 | consumed samples: 9950720 | consumed tokens: 20379074560 | elapsed time per iteration (s): 0.78 | learning rate: 2.019E-05 | global batch size: 256 | lm loss: 2.084560E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.844 | TFLOPs: 19.83 | +31: iteration 38880/ 39672 | consumed samples: 9953280 | consumed tokens: 20384317440 | elapsed time per iteration (s): 0.85 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 2.084552E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.541 | TFLOPs: 18.30 | +31: iteration 38890/ 39672 | consumed samples: 9955840 | consumed tokens: 20389560320 | elapsed time per iteration (s): 0.79 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 2.067493E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.733 | TFLOPs: 19.59 | +31: iteration 38900/ 39672 | consumed samples: 9958400 | consumed tokens: 20394803200 | elapsed time per iteration (s): 0.74 | learning rate: 2.017E-05 | global batch size: 256 | lm loss: 2.058835E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 346.240 | TFLOPs: 20.95 | +31: iteration 38910/ 39672 | consumed samples: 9960960 | consumed tokens: 20400046080 | elapsed time per iteration (s): 0.78 | learning rate: 2.017E-05 | global batch size: 256 | lm loss: 2.064441E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.748 | TFLOPs: 19.89 | +31: iteration 38920/ 39672 | consumed samples: 9963520 | consumed tokens: 20405288960 | elapsed time per iteration (s): 0.77 | learning rate: 2.016E-05 | global batch size: 256 | lm loss: 2.072121E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.620 | TFLOPs: 20.12 | +31: iteration 38930/ 39672 | consumed samples: 9966080 | consumed tokens: 20410531840 | elapsed time per iteration (s): 0.80 | learning rate: 2.016E-05 | global batch size: 256 | lm loss: 2.069324E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.223 | TFLOPs: 19.31 | +31: iteration 38940/ 39672 | consumed samples: 9968640 | consumed tokens: 20415774720 | elapsed time per iteration (s): 1.02 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 2.061461E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 251.028 | TFLOPs: 15.19 | +31: iteration 38950/ 39672 | consumed samples: 9971200 | consumed tokens: 20421017600 | elapsed time per iteration (s): 1.21 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 2.070010E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.809 | TFLOPs: 12.81 | +31: iteration 38960/ 39672 | consumed samples: 9973760 | consumed tokens: 20426260480 | elapsed time per iteration (s): 9.93 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 2.062793E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 25.771 | TFLOPs: 1.56 | +31: iteration 38970/ 39672 | consumed samples: 9976320 | consumed tokens: 20431503360 | elapsed time per iteration (s): 11.27 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 2.075811E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 22.711 | TFLOPs: 1.37 | +31: iteration 38980/ 39672 | consumed samples: 9978880 | consumed tokens: 20436746240 | elapsed time per iteration (s): 7.24 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 2.062203E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 35.380 | TFLOPs: 2.14 | +31: iteration 38990/ 39672 | consumed samples: 9981440 | consumed tokens: 20441989120 | elapsed time per iteration (s): 4.12 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 2.057640E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 62.118 | TFLOPs: 3.76 | +31: iteration 39000/ 39672 | consumed samples: 9984000 | consumed tokens: 20447232000 | elapsed time per iteration (s): 0.72 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 2.064614E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 355.195 | TFLOPs: 21.49 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 39000 | lm loss value: 2.000053E+00 | lm loss PPL: 7.389449E+00 | +31: ------------------------------------------------------------------------------------------- +31: iteration 39010/ 39672 | consumed samples: 9986560 | consumed tokens: 20452474880 | elapsed time per iteration (s): 0.76 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 2.106715E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.746 | TFLOPs: 20.25 | +31: iteration 39020/ 39672 | consumed samples: 9989120 | consumed tokens: 20457717760 | elapsed time per iteration (s): 0.76 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 2.092010E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.112 | TFLOPs: 20.39 | +31: iteration 39030/ 39672 | consumed samples: 9991680 | consumed tokens: 20462960640 | elapsed time per iteration (s): 0.72 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 2.033280E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.824 | TFLOPs: 21.59 | +31: iteration 39040/ 39672 | consumed samples: 9994240 | consumed tokens: 20468203520 | elapsed time per iteration (s): 0.72 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 2.079625E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.742 | TFLOPs: 21.46 | +31: iteration 39050/ 39672 | consumed samples: 9996800 | consumed tokens: 20473446400 | elapsed time per iteration (s): 0.72 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.053883E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.381 | TFLOPs: 21.62 | +31: iteration 39060/ 39672 | consumed samples: 9999360 | consumed tokens: 20478689280 | elapsed time per iteration (s): 0.93 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.073977E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 276.544 | TFLOPs: 16.73 | +31: iteration 39070/ 39672 | consumed samples: 10001920 | consumed tokens: 20483932160 | elapsed time per iteration (s): 0.78 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 2.032390E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.178 | TFLOPs: 19.91 | +31: iteration 39080/ 39672 | consumed samples: 10004480 | consumed tokens: 20489175040 | elapsed time per iteration (s): 1.02 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 2.086044E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 250.672 | TFLOPs: 15.17 | +31: iteration 39090/ 39672 | consumed samples: 10007040 | consumed tokens: 20494417920 | elapsed time per iteration (s): 1.25 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 2.071668E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.024 | TFLOPs: 12.40 | +31: iteration 39100/ 39672 | consumed samples: 10009600 | consumed tokens: 20499660800 | elapsed time per iteration (s): 1.94 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.058784E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 132.185 | TFLOPs: 8.00 | +31: iteration 39110/ 39672 | consumed samples: 10012160 | consumed tokens: 20504903680 | elapsed time per iteration (s): 5.50 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.047347E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 46.583 | TFLOPs: 2.82 | +31: iteration 39120/ 39672 | consumed samples: 10014720 | consumed tokens: 20510146560 | elapsed time per iteration (s): 8.13 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.077113E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 31.474 | TFLOPs: 1.90 | +31: iteration 39130/ 39672 | consumed samples: 10017280 | consumed tokens: 20515389440 | elapsed time per iteration (s): 6.82 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.071970E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 37.535 | TFLOPs: 2.27 | +31: iteration 39140/ 39672 | consumed samples: 10019840 | consumed tokens: 20520632320 | elapsed time per iteration (s): 7.50 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.054841E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 34.146 | TFLOPs: 2.07 | +31: iteration 39150/ 39672 | consumed samples: 10022400 | consumed tokens: 20525875200 | elapsed time per iteration (s): 6.75 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.063354E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 37.920 | TFLOPs: 2.29 | +31: iteration 39160/ 39672 | consumed samples: 10024960 | consumed tokens: 20531118080 | elapsed time per iteration (s): 6.26 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.055824E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 40.877 | TFLOPs: 2.47 | +31: iteration 39170/ 39672 | consumed samples: 10027520 | consumed tokens: 20536360960 | elapsed time per iteration (s): 4.56 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.070848E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 56.181 | TFLOPs: 3.40 | +31: iteration 39180/ 39672 | consumed samples: 10030080 | consumed tokens: 20541603840 | elapsed time per iteration (s): 5.69 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.080583E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 44.962 | TFLOPs: 2.72 | +31: iteration 39190/ 39672 | consumed samples: 10032640 | consumed tokens: 20546846720 | elapsed time per iteration (s): 5.89 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.048592E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 43.450 | TFLOPs: 2.63 | +31: iteration 39200/ 39672 | consumed samples: 10035200 | consumed tokens: 20552089600 | elapsed time per iteration (s): 6.63 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.060190E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 38.609 | TFLOPs: 2.34 | +31: iteration 39210/ 39672 | consumed samples: 10037760 | consumed tokens: 20557332480 | elapsed time per iteration (s): 6.72 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.049813E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 38.105 | TFLOPs: 2.31 | +31: iteration 39220/ 39672 | consumed samples: 10040320 | consumed tokens: 20562575360 | elapsed time per iteration (s): 6.65 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.069782E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 38.516 | TFLOPs: 2.33 | +31: iteration 39230/ 39672 | consumed samples: 10042880 | consumed tokens: 20567818240 | elapsed time per iteration (s): 6.31 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.044176E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 40.550 | TFLOPs: 2.45 | +31: iteration 39240/ 39672 | consumed samples: 10045440 | consumed tokens: 20573061120 | elapsed time per iteration (s): 5.98 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.057641E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 42.840 | TFLOPs: 2.59 | +31: iteration 39250/ 39672 | consumed samples: 10048000 | consumed tokens: 20578304000 | elapsed time per iteration (s): 0.77 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.029526E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.069 | TFLOPs: 20.21 | +31: iteration 39260/ 39672 | consumed samples: 10050560 | consumed tokens: 20583546880 | elapsed time per iteration (s): 0.80 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.052720E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.594 | TFLOPs: 19.27 | +31: iteration 39270/ 39672 | consumed samples: 10053120 | consumed tokens: 20588789760 | elapsed time per iteration (s): 0.77 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.057324E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.211 | TFLOPs: 20.04 | +31: iteration 39280/ 39672 | consumed samples: 10055680 | consumed tokens: 20594032640 | elapsed time per iteration (s): 0.76 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.072799E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.896 | TFLOPs: 20.38 | +31: iteration 39290/ 39672 | consumed samples: 10058240 | consumed tokens: 20599275520 | elapsed time per iteration (s): 0.82 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.068041E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.684 | TFLOPs: 18.98 | +31: iteration 39300/ 39672 | consumed samples: 10060800 | consumed tokens: 20604518400 | elapsed time per iteration (s): 0.74 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.087065E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.442 | TFLOPs: 21.02 | +31: iteration 39310/ 39672 | consumed samples: 10063360 | consumed tokens: 20609761280 | elapsed time per iteration (s): 0.75 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.106514E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.554 | TFLOPs: 20.66 | +31: iteration 39320/ 39672 | consumed samples: 10065920 | consumed tokens: 20615004160 | elapsed time per iteration (s): 0.73 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.034356E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 350.877 | TFLOPs: 21.23 | +31: iteration 39330/ 39672 | consumed samples: 10068480 | consumed tokens: 20620247040 | elapsed time per iteration (s): 0.77 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.073053E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.303 | TFLOPs: 20.22 | +31: iteration 39340/ 39672 | consumed samples: 10071040 | consumed tokens: 20625489920 | elapsed time per iteration (s): 0.74 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.068040E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 347.169 | TFLOPs: 21.00 | +31: iteration 39350/ 39672 | consumed samples: 10073600 | consumed tokens: 20630732800 | elapsed time per iteration (s): 0.78 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.058312E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.345 | TFLOPs: 19.80 | +31: iteration 39360/ 39672 | consumed samples: 10076160 | consumed tokens: 20635975680 | elapsed time per iteration (s): 0.77 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.067595E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.689 | TFLOPs: 20.01 | +31: iteration 39370/ 39672 | consumed samples: 10078720 | consumed tokens: 20641218560 | elapsed time per iteration (s): 0.73 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.042612E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 349.545 | TFLOPs: 21.15 | +31: iteration 39380/ 39672 | consumed samples: 10081280 | consumed tokens: 20646461440 | elapsed time per iteration (s): 0.76 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.077568E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.557 | TFLOPs: 20.30 | +31: iteration 39390/ 39672 | consumed samples: 10083840 | consumed tokens: 20651704320 | elapsed time per iteration (s): 0.78 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.093535E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.106 | TFLOPs: 19.85 | +31: iteration 39400/ 39672 | consumed samples: 10086400 | consumed tokens: 20656947200 | elapsed time per iteration (s): 0.81 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.042744E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 317.830 | TFLOPs: 19.23 | +31: iteration 39410/ 39672 | consumed samples: 10088960 | consumed tokens: 20662190080 | elapsed time per iteration (s): 0.78 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.022760E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.226 | TFLOPs: 19.86 | +31: iteration 39420/ 39672 | consumed samples: 10091520 | consumed tokens: 20667432960 | elapsed time per iteration (s): 0.83 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.059264E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.810 | TFLOPs: 18.62 | +31: iteration 39430/ 39672 | consumed samples: 10094080 | consumed tokens: 20672675840 | elapsed time per iteration (s): 0.80 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.076543E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.244 | TFLOPs: 19.31 | +31: iteration 39440/ 39672 | consumed samples: 10096640 | consumed tokens: 20677918720 | elapsed time per iteration (s): 0.82 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.068241E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.364 | TFLOPs: 18.96 | +31: iteration 39450/ 39672 | consumed samples: 10099200 | consumed tokens: 20683161600 | elapsed time per iteration (s): 0.78 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.076341E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.757 | TFLOPs: 19.95 | +31: iteration 39460/ 39672 | consumed samples: 10101760 | consumed tokens: 20688404480 | elapsed time per iteration (s): 0.77 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.090557E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.344 | TFLOPs: 20.17 | +31: iteration 39470/ 39672 | consumed samples: 10104320 | consumed tokens: 20693647360 | elapsed time per iteration (s): 0.82 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.067471E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.133 | TFLOPs: 18.94 | +31: iteration 39480/ 39672 | consumed samples: 10106880 | consumed tokens: 20698890240 | elapsed time per iteration (s): 0.83 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.077328E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 307.910 | TFLOPs: 18.63 | +31: iteration 39490/ 39672 | consumed samples: 10109440 | consumed tokens: 20704133120 | elapsed time per iteration (s): 0.81 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.085644E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.313 | TFLOPs: 19.02 | +31: iteration 39500/ 39672 | consumed samples: 10112000 | consumed tokens: 20709376000 | elapsed time per iteration (s): 0.84 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.076461E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 304.889 | TFLOPs: 18.44 | +31: iteration 39510/ 39672 | consumed samples: 10114560 | consumed tokens: 20714618880 | elapsed time per iteration (s): 0.78 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.058706E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.723 | TFLOPs: 19.77 | +31: iteration 39520/ 39672 | consumed samples: 10117120 | consumed tokens: 20719861760 | elapsed time per iteration (s): 0.80 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.045736E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.087 | TFLOPs: 19.30 | +31: iteration 39530/ 39672 | consumed samples: 10119680 | consumed tokens: 20725104640 | elapsed time per iteration (s): 0.82 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.063587E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 313.640 | TFLOPs: 18.97 | +31: iteration 39540/ 39672 | consumed samples: 10122240 | consumed tokens: 20730347520 | elapsed time per iteration (s): 0.83 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.058724E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 306.906 | TFLOPs: 18.57 | +31: iteration 39550/ 39672 | consumed samples: 10124800 | consumed tokens: 20735590400 | elapsed time per iteration (s): 0.76 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.049970E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.745 | TFLOPs: 20.31 | +31: iteration 39560/ 39672 | consumed samples: 10127360 | consumed tokens: 20740833280 | elapsed time per iteration (s): 0.84 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.044269E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.311 | TFLOPs: 18.35 | +31: iteration 39570/ 39672 | consumed samples: 10129920 | consumed tokens: 20746076160 | elapsed time per iteration (s): 0.83 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.054451E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 308.220 | TFLOPs: 18.65 | +31: iteration 39580/ 39672 | consumed samples: 10132480 | consumed tokens: 20751319040 | elapsed time per iteration (s): 0.87 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.060604E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.323 | TFLOPs: 17.87 | +31: iteration 39590/ 39672 | consumed samples: 10135040 | consumed tokens: 20756561920 | elapsed time per iteration (s): 0.78 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.043096E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.293 | TFLOPs: 19.86 | +31: iteration 39600/ 39672 | consumed samples: 10137600 | consumed tokens: 20761804800 | elapsed time per iteration (s): 0.78 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.070625E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.351 | TFLOPs: 19.74 | +31: iteration 39610/ 39672 | consumed samples: 10140160 | consumed tokens: 20767047680 | elapsed time per iteration (s): 0.85 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.073398E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.947 | TFLOPs: 18.27 | +31: iteration 39620/ 39672 | consumed samples: 10142720 | consumed tokens: 20772290560 | elapsed time per iteration (s): 0.81 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.083463E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 314.831 | TFLOPs: 19.05 | +31: iteration 39630/ 39672 | consumed samples: 10145280 | consumed tokens: 20777533440 | elapsed time per iteration (s): 0.78 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.074043E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.618 | TFLOPs: 19.82 | +31: iteration 39640/ 39672 | consumed samples: 10147840 | consumed tokens: 20782776320 | elapsed time per iteration (s): 0.80 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.060862E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 318.545 | TFLOPs: 19.27 | +31: iteration 39650/ 39672 | consumed samples: 10150400 | consumed tokens: 20788019200 | elapsed time per iteration (s): 0.85 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.051619E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.660 | TFLOPs: 18.25 | +31: iteration 39660/ 39672 | consumed samples: 10152960 | consumed tokens: 20793262080 | elapsed time per iteration (s): 0.78 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.099471E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.791 | TFLOPs: 19.95 | +31: iteration 39670/ 39672 | consumed samples: 10155520 | consumed tokens: 20798504960 | elapsed time per iteration (s): 0.83 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.047160E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 310.042 | TFLOPs: 18.76 | + 0: [after training is done] datetime: 2022-11-30 19:32:22 + 0: saving checkpoint at iteration 39672 to checkpoints_1b121b +31: ------------------------------------------------------------------------------------------------------------ +31: valid loss at the end of training for val data | lm loss value: 1.996720E+00 | lm loss PPL: 7.364860E+00 | +31: ------------------------------------------------------------------------------------------------------------ + 0: [2022-11-30 19:32:22,296] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step39672 is begin to save! + 0: [2022-11-30 19:32:22,394] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_01-model_00-model_states.pt... + 0: [2022-11-30 19:32:22,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_01-model_00-model_states.pt. + 0: [2022-11-30 19:32:22,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_03-model_00-model_states.pt... + 0: [2022-11-30 19:32:22,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_03-model_00-model_states.pt. + 0: [2022-11-30 19:32:22,847] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_04-model_00-model_states.pt... + 0: [2022-11-30 19:32:22,934] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_04-model_00-model_states.pt. + 0: [2022-11-30 19:32:22,934] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_05-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_05-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_06-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_06-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,112] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_07-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_07-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,193] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_08-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_08-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,275] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_09-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_09-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,356] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_10-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_10-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_11-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_11-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,517] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_12-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_12-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,597] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_13-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_13-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,675] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_14-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_14-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,755] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_15-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_15-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,831] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_16-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_16-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,909] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_17-model_00-model_states.pt... + 0: [2022-11-30 19:32:23,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_17-model_00-model_states.pt. + 0: [2022-11-30 19:32:23,985] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_18-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,072] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_18-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,072] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_19-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_19-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,146] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_20-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_20-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_21-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_21-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,295] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_22-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_22-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,370] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_23-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_23-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,448] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_24-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_24-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_25-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_25-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,604] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_26-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_26-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,676] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_27-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_27-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,755] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_28-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_28-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,829] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/layer_30-model_00-model_states.pt... + 0: [2022-11-30 19:32:24,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/layer_30-model_00-model_states.pt. + 0: [2022-11-30 19:32:24,836] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_1b121b/global_step39672/mp_rank_00_model_states.pt + 0: [2022-11-30 19:32:24,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/mp_rank_00_model_states.pt... + 0: [2022-11-30 19:32:24,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/mp_rank_00_model_states.pt. + 0: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +24: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +31: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... + 0: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +20: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +15: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... + 0: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +12: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... + 8: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 3: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +21: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +29: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +24: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +27: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +31: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 7: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 9: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +11: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +20: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +17: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +15: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +14: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +18: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... + 0: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +19: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +12: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... + 8: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 3: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +23: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +21: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +29: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +24: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... + 5: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +13: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +30: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +10: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... + 6: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +27: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +31: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 7: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 9: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +11: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +20: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +17: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +22: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +26: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +16: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... + 1: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +15: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... + 2: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 4: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +14: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +18: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +28: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... + 0: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +19: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +12: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... + 8: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 3: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +23: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +21: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +29: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +24: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... + 5: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +13: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +30: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +10: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... + 6: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +27: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +31: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 7: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 9: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +11: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +20: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +17: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +22: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +26: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +16: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... + 1: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +15: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... + 2: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 4: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +14: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +18: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +28: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... + 0: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +12: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... + 8: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 3: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +23: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +21: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +24: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... + 5: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +13: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +30: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +10: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... + 6: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +27: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +25: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +31: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +20: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +17: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +22: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +26: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +16: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... + 1: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +15: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... + 2: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 4: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +14: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +18: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +28: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +12: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... + 3: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +23: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +13: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... + 6: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +25: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +26: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +14: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +18: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +25: [2022-11-30 19:32:24,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +14: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +18: [2022-11-30 19:32:24,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... + 0: [2022-11-30 19:32:24,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 0: [2022-11-30 19:32:24,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-30 19:32:24,972] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-30 19:32:24,972] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 0: [2022-11-30 19:32:24,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-30 19:32:24,979] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-30 19:32:24,979] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 0: [2022-11-30 19:32:24,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-30 19:32:24,979] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-30 19:32:24,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 0: [2022-11-30 19:32:24,987] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-30 19:32:24,987] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-30 19:32:24,987] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-30 19:32:24,987] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-30 19:32:24,987] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 0: [2022-11-30 19:32:24,987] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +11: [2022-11-30 19:32:25,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-30 19:32:25,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-30 19:32:25,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-30 19:32:25,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-30 19:32:25,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +11: [2022-11-30 19:32:25,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +11: [2022-11-30 19:32:25,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-30 19:32:25,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-30 19:32:25,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +11: [2022-11-30 19:32:25,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-30 19:32:25,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-30 19:32:25,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +11: [2022-11-30 19:32:25,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-30 19:32:25,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-30 19:32:25,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-30 19:32:25,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-30 19:32:25,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-30 19:32:25,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-30 19:32:25,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +11: [2022-11-30 19:32:25,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +11: [2022-11-30 19:32:25,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 0: [2022-11-30 19:32:25,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-30 19:32:25,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-30 19:32:25,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-30 19:32:25,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-30 19:32:25,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 0: [2022-11-30 19:32:25,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +11: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-30 19:32:25,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +26: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-30 19:32:25,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +26: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-30 19:32:25,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-30 19:32:25,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +26: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +26: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-30 19:32:25,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +26: [2022-11-30 19:32:25,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-30 19:32:25,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +21: [2022-11-30 19:32:25,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-30 19:32:25,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-30 19:32:25,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-30 19:32:25,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-30 19:32:25,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +21: [2022-11-30 19:32:25,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +21: [2022-11-30 19:32:25,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-30 19:32:25,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-30 19:32:25,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-30 19:32:25,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-30 19:32:25,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-30 19:32:25,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +21: [2022-11-30 19:32:25,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-30 19:32:25,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +21: [2022-11-30 19:32:25,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +31: [2022-11-30 19:32:25,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-30 19:32:25,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-30 19:32:25,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-30 19:32:25,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-30 19:32:25,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-30 19:32:25,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-30 19:32:25,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-30 19:32:25,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-30 19:32:25,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-30 19:32:25,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-30 19:32:25,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-30 19:32:25,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +31: [2022-11-30 19:32:25,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +31: [2022-11-30 19:32:25,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-30 19:32:25,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +31: [2022-11-30 19:32:25,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-30 19:32:25,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-30 19:32:25,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +31: [2022-11-30 19:32:25,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +31: [2022-11-30 19:32:25,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +31: [2022-11-30 19:32:25,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +26: [2022-11-30 19:32:25,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-30 19:32:25,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-30 19:32:25,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-30 19:32:25,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-30 19:32:25,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-30 19:32:25,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-30 19:32:25,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +26: [2022-11-30 19:32:25,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +26: [2022-11-30 19:32:25,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +21: [2022-11-30 19:32:25,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-30 19:32:25,045] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-30 19:32:25,045] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 8: [2022-11-30 19:32:25,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-30 19:32:25,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-30 19:32:25,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-30 19:32:25,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-30 19:32:25,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-30 19:32:25,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-30 19:32:25,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-30 19:32:25,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-30 19:32:25,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-30 19:32:25,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 8: [2022-11-30 19:32:25,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-30 19:32:25,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 8: [2022-11-30 19:32:25,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 8: [2022-11-30 19:32:25,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 8: [2022-11-30 19:32:25,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-30 19:32:25,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-30 19:32:25,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-30 19:32:25,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-30 19:32:25,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-30 19:32:25,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-30 19:32:25,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-30 19:32:25,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +27: [2022-11-30 19:32:25,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +15: [2022-11-30 19:32:25,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-30 19:32:25,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +23: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-30 19:32:25,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-30 19:32:25,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-30 19:32:25,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-30 19:32:25,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +23: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +23: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +23: [2022-11-30 19:32:25,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +23: [2022-11-30 19:32:25,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +15: [2022-11-30 19:32:25,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-30 19:32:25,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-30 19:32:25,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +15: [2022-11-30 19:32:25,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-30 19:32:25,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-30 19:32:25,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-30 19:32:25,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-30 19:32:25,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +15: [2022-11-30 19:32:25,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +15: [2022-11-30 19:32:25,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-30 19:32:25,066] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-30 19:32:25,066] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 4: [2022-11-30 19:32:25,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-30 19:32:25,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-30 19:32:25,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 4: [2022-11-30 19:32:25,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-30 19:32:25,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-30 19:32:25,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-30 19:32:25,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-30 19:32:25,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-30 19:32:25,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-30 19:32:25,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-30 19:32:25,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +10: [2022-11-30 19:32:25,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +10: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +15: [2022-11-30 19:32:25,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-30 19:32:25,073] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-30 19:32:25,073] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +21: [2022-11-30 19:32:25,074] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-30 19:32:25,074] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-30 19:32:25,074] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +19: [2022-11-30 19:32:25,074] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +23: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +19: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +23: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +19: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 4: [2022-11-30 19:32:25,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-30 19:32:25,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 4: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-30 19:32:25,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-30 19:32:25,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 4: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 4: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-30 19:32:25,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 4: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 4: [2022-11-30 19:32:25,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +27: [2022-11-30 19:32:25,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-30 19:32:25,078] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-30 19:32:25,078] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 3: [2022-11-30 19:32:25,079] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-30 19:32:25,079] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-30 19:32:25,079] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-30 19:32:25,079] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-30 19:32:25,079] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-30 19:32:25,079] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-30 19:32:25,080] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 3: [2022-11-30 19:32:25,080] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 3: [2022-11-30 19:32:25,080] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 3: [2022-11-30 19:32:25,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-30 19:32:25,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-30 19:32:25,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-30 19:32:25,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-30 19:32:25,082] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-30 19:32:25,082] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-30 19:32:25,082] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-30 19:32:25,082] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-30 19:32:25,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 3: [2022-11-30 19:32:25,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 3: [2022-11-30 19:32:25,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 3: [2022-11-30 19:32:25,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-30 19:32:25,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-30 19:32:25,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-30 19:32:25,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-30 19:32:25,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-30 19:32:25,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-30 19:32:25,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-30 19:32:25,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +20: [2022-11-30 19:32:25,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-30 19:32:25,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-30 19:32:25,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-30 19:32:25,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-30 19:32:25,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-30 19:32:25,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +20: [2022-11-30 19:32:25,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +20: [2022-11-30 19:32:25,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-30 19:32:25,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +20: [2022-11-30 19:32:25,088] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-30 19:32:25,088] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-30 19:32:25,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-30 19:32:25,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-30 19:32:25,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-30 19:32:25,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-30 19:32:25,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-30 19:32:25,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-30 19:32:25,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +24: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +10: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-30 19:32:25,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-30 19:32:25,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +24: [2022-11-30 19:32:25,090] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-30 19:32:25,090] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-30 19:32:25,090] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +20: [2022-11-30 19:32:25,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-30 19:32:25,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-30 19:32:25,091] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-30 19:32:25,091] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-30 19:32:25,091] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +20: [2022-11-30 19:32:25,091] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +20: [2022-11-30 19:32:25,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-30 19:32:25,091] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-30 19:32:25,091] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +14: [2022-11-30 19:32:25,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-30 19:32:25,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-30 19:32:25,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-30 19:32:25,092] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-30 19:32:25,092] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-30 19:32:25,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +14: [2022-11-30 19:32:25,092] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-30 19:32:25,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +14: [2022-11-30 19:32:25,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +31: [2022-11-30 19:32:25,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-30 19:32:25,094] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-30 19:32:25,094] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 8: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-30 19:32:25,095] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +10: [2022-11-30 19:32:25,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-30 19:32:25,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-30 19:32:25,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 9: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-30 19:32:25,095] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-30 19:32:25,095] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 9: [2022-11-30 19:32:25,095] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-30 19:32:25,095] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 9: [2022-11-30 19:32:25,095] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-30 19:32:25,095] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-30 19:32:25,095] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-30 19:32:25,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-30 19:32:25,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 9: [2022-11-30 19:32:25,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 9: [2022-11-30 19:32:25,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 9: [2022-11-30 19:32:25,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 9: [2022-11-30 19:32:25,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 7: [2022-11-30 19:32:25,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-30 19:32:25,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-30 19:32:25,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-30 19:32:25,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-30 19:32:25,097] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-30 19:32:25,097] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-30 19:32:25,097] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-30 19:32:25,097] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-30 19:32:25,097] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 7: [2022-11-30 19:32:25,097] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 7: [2022-11-30 19:32:25,097] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 7: [2022-11-30 19:32:25,097] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +23: [2022-11-30 19:32:25,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-30 19:32:25,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-30 19:32:25,098] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-30 19:32:25,098] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-30 19:32:25,098] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +23: [2022-11-30 19:32:25,098] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 7: [2022-11-30 19:32:25,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-30 19:32:25,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-30 19:32:25,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-30 19:32:25,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-30 19:32:25,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-30 19:32:25,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-30 19:32:25,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 7: [2022-11-30 19:32:25,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 7: [2022-11-30 19:32:25,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 3: [2022-11-30 19:32:25,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-30 19:32:25,101] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 0: [2022-11-30 19:32:25,101] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 3: [2022-11-30 19:32:25,101] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 0: [2022-11-30 19:32:25,101] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +21: [2022-11-30 19:32:25,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-30 19:32:25,101] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-30 19:32:25,101] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +14: [2022-11-30 19:32:25,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-30 19:32:25,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-30 19:32:25,102] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-30 19:32:25,102] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-30 19:32:25,102] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +14: [2022-11-30 19:32:25,102] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +14: [2022-11-30 19:32:25,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-30 19:32:25,102] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-30 19:32:25,102] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +25: [2022-11-30 19:32:25,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-30 19:32:25,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-30 19:32:25,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-30 19:32:25,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-30 19:32:25,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-30 19:32:25,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-30 19:32:25,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-30 19:32:25,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-30 19:32:25,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-30 19:32:25,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-30 19:32:25,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +25: [2022-11-30 19:32:25,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +25: [2022-11-30 19:32:25,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +25: [2022-11-30 19:32:25,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +25: [2022-11-30 19:32:25,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +15: [2022-11-30 19:32:25,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-30 19:32:25,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-30 19:32:25,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 8: [2022-11-30 19:32:25,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-30 19:32:25,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-30 19:32:25,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt + 2: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. + 2: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 2: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +13: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +13: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt + 2: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +13: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +13: [2022-11-30 19:32:25,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 2: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +13: [2022-11-30 19:32:25,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +28: [2022-11-30 19:32:25,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +19: [2022-11-30 19:32:25,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-30 19:32:25,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-30 19:32:25,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +28: [2022-11-30 19:32:25,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-30 19:32:25,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +28: [2022-11-30 19:32:25,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-30 19:32:25,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-30 19:32:25,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-30 19:32:25,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-30 19:32:25,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-30 19:32:25,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-30 19:32:25,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +28: [2022-11-30 19:32:25,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +28: [2022-11-30 19:32:25,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +28: [2022-11-30 19:32:25,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. + 7: [2022-11-30 19:32:25,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-30 19:32:25,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-30 19:32:25,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +19: [2022-11-30 19:32:25,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-30 19:32:25,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-30 19:32:25,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +28: [2022-11-30 19:32:25,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-30 19:32:25,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-30 19:32:25,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +28: [2022-11-30 19:32:25,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-30 19:32:25,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-30 19:32:25,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +28: [2022-11-30 19:32:25,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-30 19:32:25,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 8: [2022-11-30 19:32:25,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-30 19:32:25,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-30 19:32:25,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +20: [2022-11-30 19:32:25,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-30 19:32:25,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-30 19:32:25,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-30 19:32:25,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-30 19:32:25,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-30 19:32:25,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-30 19:32:25,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-30 19:32:25,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-30 19:32:25,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-30 19:32:25,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +29: [2022-11-30 19:32:25,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-30 19:32:25,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-30 19:32:25,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-30 19:32:25,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 5: [2022-11-30 19:32:25,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-30 19:32:25,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-30 19:32:25,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 5: [2022-11-30 19:32:25,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +25: [2022-11-30 19:32:25,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-30 19:32:25,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-30 19:32:25,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +17: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-30 19:32:25,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-30 19:32:25,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-30 19:32:25,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-30 19:32:25,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-30 19:32:25,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-30 19:32:25,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-30 19:32:25,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +16: [2022-11-30 19:32:25,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 6: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +18: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-30 19:32:25,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +18: [2022-11-30 19:32:25,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 5: [2022-11-30 19:32:25,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 1: [2022-11-30 19:32:25,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-30 19:32:25,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-30 19:32:25,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-30 19:32:25,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-30 19:32:25,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 5: [2022-11-30 19:32:25,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 1: [2022-11-30 19:32:25,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-30 19:32:25,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 1: [2022-11-30 19:32:25,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 5: [2022-11-30 19:32:25,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 1: [2022-11-30 19:32:25,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +17: [2022-11-30 19:32:25,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-30 19:32:25,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-30 19:32:25,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +16: [2022-11-30 19:32:25,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-30 19:32:25,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-30 19:32:25,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 1: [2022-11-30 19:32:25,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-30 19:32:25,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-30 19:32:25,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 1: [2022-11-30 19:32:25,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-30 19:32:25,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-30 19:32:25,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-30 19:32:25,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-30 19:32:25,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-30 19:32:25,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 1: [2022-11-30 19:32:25,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-30 19:32:25,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 1: [2022-11-30 19:32:25,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 1: [2022-11-30 19:32:25,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-30 19:32:25,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-30 19:32:25,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-30 19:32:25,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-30 19:32:25,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-30 19:32:25,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-30 19:32:25,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-30 19:32:25,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-30 19:32:25,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +12: [2022-11-30 19:32:25,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +14: [2022-11-30 19:32:25,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-30 19:32:25,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-30 19:32:25,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +15: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +30: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +15: [2022-11-30 19:32:25,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +30: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-30 19:32:25,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-30 19:32:25,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-30 19:32:25,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt + 5: [2022-11-30 19:32:25,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +30: [2022-11-30 19:32:25,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +30: [2022-11-30 19:32:25,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-30 19:32:25,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-30 19:32:25,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-30 19:32:25,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +30: [2022-11-30 19:32:25,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 5: [2022-11-30 19:32:25,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +30: [2022-11-30 19:32:25,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-30 19:32:25,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt + 5: [2022-11-30 19:32:25,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +30: [2022-11-30 19:32:25,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +30: [2022-11-30 19:32:25,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +30: [2022-11-30 19:32:25,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +30: [2022-11-30 19:32:25,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +30: [2022-11-30 19:32:25,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +14: [2022-11-30 19:32:25,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-30 19:32:25,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-30 19:32:25,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-30 19:32:25,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-30 19:32:25,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-30 19:32:25,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-30 19:32:25,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-30 19:32:25,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +22: [2022-11-30 19:32:25,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-30 19:32:25,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-30 19:32:25,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +22: [2022-11-30 19:32:25,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +12: [2022-11-30 19:32:25,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-30 19:32:25,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-30 19:32:25,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 6: [2022-11-30 19:32:25,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-30 19:32:25,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-30 19:32:25,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 9: [2022-11-30 19:32:25,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-30 19:32:25,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-30 19:32:25,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +25: [2022-11-30 19:32:25,181] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-30 19:32:25,181] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-30 19:32:25,181] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +16: [2022-11-30 19:32:25,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-30 19:32:25,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-30 19:32:25,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +28: [2022-11-30 19:32:25,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-30 19:32:25,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-30 19:32:25,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +25: [2022-11-30 19:32:25,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-30 19:32:25,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-30 19:32:25,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +29: [2022-11-30 19:32:25,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-30 19:32:25,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-30 19:32:25,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 6: [2022-11-30 19:32:25,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-30 19:32:25,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-30 19:32:25,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! +12: [2022-11-30 19:32:25,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-30 19:32:25,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b121b/global_step39672/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-30 19:32:25,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step39672 is ready now! + 0: successfully saved checkpoint at iteration 39672 to checkpoints_1b121b +31: ------------------------------------------------------------------------------------------------------------ +31: test loss at the end of training for test data | lm loss value: 2.021729E+00 | lm loss PPL: 7.551372E+00 | +31: ------------------------------------------------------------------------------------------------------------ +END 2088000: Wed Nov 30 19:32:38 EET 2022 diff --git a/1b121b21b/sbatch_1b121b.sh b/1b121b21b/sbatch_1b121b.sh new file mode 100644 index 0000000000000000000000000000000000000000..5d6f8af9ab5880064b9dba49a037dfb256a70b73 --- /dev/null +++ b/1b121b21b/sbatch_1b121b.sh @@ -0,0 +1,159 @@ +#!/bin/bash +#SBATCH --exclude=nid007571,nid007112,nid006774,nid007502,nid007506,nid007507,nid005145,nid006692,nid007218,nid007123,nid006124,nid006123,nid007496,nid007237,nid006852,nid007206,nid006947,nid007212,nid006977,nid007222,nid005444,nid007219,nid007493,nid007221,nid005300,nid005619,nid006118,nid005203,nid006113,nid006481,nid007077,nid005208,nid005207,nid005879,nid005901 +#SBATCH --nodes=32 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=256G +#SBATCH -p pilot +#SBATCH -t 48:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --exclusive=user +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=1b121b + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document" + +PP_SIZE=1 +TP_SIZE=1 + +MICRO_BATCH_SIZE=1 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_1143M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=10000 + +# Tokens: 20_800_000_000 +# -> Samples: 10156250 +TRAIN_SAMPLES=10_156_250 + +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 101_563 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/1b121b21b/tensorboard_1b121b/events.out.tfevents.1669792426.nid006156.112528.0 b/1b121b21b/tensorboard_1b121b/events.out.tfevents.1669792426.nid006156.112528.0 new file mode 100644 index 0000000000000000000000000000000000000000..20262b5de6584f7f4b3258e5f498d98edb2eca82 --- /dev/null +++ b/1b121b21b/tensorboard_1b121b/events.out.tfevents.1669792426.nid006156.112528.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66dea8b7e368bad1be8d4ee4f0eb3ba300c888f9cbd82aa5dbae90ecb99a553b +size 70920951